[
{
"name": "thetom-27b-q3xl-mtp-np3-192k",
"model": "C:\\Users\\sjake\\LLM\\models\\unsloth-qwen3.6-27b-mtp-gguf\\Qwen3.6-27B-UD-Q3_K_XL.gguf",
"mtp": true,
"log": "C:\\Users\\sjake\\LLM\\logs\\thetom-27b-q3xl-mtp-np3-192k-20260526-191212.loadonly.log",
"before": {
"used_mib": 1036,
"free_mib": 23278,
"power_w": 28.23,
"temp_c": 48
},
"ready": {
"used_mib": 20985,
"free_mib": 3329,
"power_w": 73.49,
"temp_c": 51
},
"stable": {
"used_mib": 20985,
"free_mib": 3329,
"power_w": 28.39,
"temp_c": 48
},
"net_ready_mib": 19949,
"props": {
"default_generation_settings": {
"params": {
"seed": 4294967295,
"temperature": 1.0,
"dynatemp_range": 0.0,
"dynatemp_exponent": 1.0,
"top_k": 20,
"top_p": 0.949999988079071,
"min_p": 0.05000000074505806,
"top_n_sigma": -1.0,
"xtc_probability": 0.0,
"xtc_threshold": 0.10000000149011612,
"typical_p": 1.0,
"repeat_last_n": 64,
"repeat_penalty": 1.0,
"presence_penalty": 0.0,
"frequency_penalty": 0.0,
"dry_multiplier": 0.0,
"dry_base": 1.75,
"dry_allowed_length": 2,
"dry_penalty_last_n": -1,
"mirostat": 0,
"mirostat_tau": 5.0,
"mirostat_eta": 0.10000000149011612,
"max_tokens": -1,
"n_predict": -1,
"n_keep": 0,
"n_discard": 0,
"ignore_eos": false,
"stream": true,
"n_probs": 0,
"min_keep": 0,
"chat_format": "Content-only",
"reasoning_format": "none",
"reasoning_in_content": false,
"generation_prompt": "",
"samplers": [
"penalties",
"dry",
"top_n_sigma",
"top_k",
"typ_p",
"top_p",
"min_p",
"xtc",
"temperature"
],
"speculative.types": "none",
"timings_per_token": false,
"post_sampling_probs": false,
"backend_sampling": false,
"lora": []
},
"n_ctx": 64000
},
"total_slots": 3,
"model_alias": "Qwen3.6-27B-UD-Q3_K_XL.gguf",
"model_path": "C:\\Users\\sjake\\LLM\\models\\unsloth-qwen3.6-27b-mtp-gguf\\Qwen3.6-27B-UD-Q3_K_XL.gguf",
"modalities": {
"vision": false,
"audio": false
},
"media_marker": "<__media_swomMRc7BRHVewX313hO8PIJxQnO8Jad__>",
"endpoint_slots": true,
"endpoint_props": false,
"endpoint_metrics": false,
"ui": false,
"ui_settings": {},
"webui": false,
"webui_settings": {},
"chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n {%- if content is string %}\n {{- content }}\n {%- elif content is iterable and content is not mapping %}\n {%- for item in content %}\n {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain images.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Picture ' ~ image_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n {%- elif 'video' in item or item.type == 'video' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain videos.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Video ' ~ video_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- else %}\n {{- raise_exception('Unexpected item type in content.') }}\n {%- endif %}\n {%- endfor %}\n {%- elif content is none or content is undefined %}\n {{- '' }}\n {%- else %}\n {{- raise_exception('Unexpected content type.') }}\n {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- set num_sys = 0 %}\n{%- set merged_system = '' %}\n{%- if messages[0].role == 'system' or messages[0].role == 'developer' %}\n {%- set first = render_content(messages[0].content, false, true)|trim %}\n {%- if messages|length > 1 and (messages[1].role == 'system' or messages[1].role == 'developer') %}\n {%- set second = render_content(messages[1].content, false, true)|trim %}\n {%- set merged_system = first + '\\n' + second %}\n {%- set num_sys = 2 %}\n {%- else %}\n {%- set merged_system = first %}\n {%- set num_sys = 1 %}\n {%- endif %}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n {{- '<|im_start|>system\\n' }}\n {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n\" }}\n {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n\\n\\n\\nvalue_1\\n\\n\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n\\n\\n\\n\\n\\nReminder:\\n- Function calls MUST follow the specified format: an inner block must be nested within XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n' }}\n {%- if merged_system %}\n {{- '\\n\\n' + merged_system }}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n{%- else %}\n {%- if merged_system %}\n {{- '<|im_start|>system\\n' + merged_system + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" %}\n {%- set content = render_content(message.content, false)|trim %}\n {%- if not(content.startswith('') and content.endswith('')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if loop.index0 >= num_sys and message.role != \"system\" and message.role != \"developer\" %}\n {%- set content = render_content(message.content, true)|trim %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '' in content %}\n {%- set reasoning_content = content.split('')[0].rstrip('\\n').split('')[-1].lstrip('\\n') %}\n {%- set content = content.split('')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- set reasoning_content = reasoning_content|trim %}\n {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}\n {{- '<|im_start|>' + message.role + '\\n\\n' + reasoning_content + '\\n\\n\\n' + content }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {%- if loop.first %}\n {%- if content|trim %}\n {{- '\\n\\n\\n\\n' }}\n {%- else %}\n {{- '\\n\\n' }}\n {%- endif %}\n {%- else %}\n {{- '\\n\\n\\n' }}\n {%- endif %}\n {%- if tool_call.arguments is mapping %}\n {%- for args_name in tool_call.arguments %}\n {%- set args_value = tool_call.arguments[args_name] %}\n {{- '\\n' }}\n {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}\n {{- args_value }}\n {{- '\\n\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n\\n' }}\n {{- content }}\n {{- '\\n' }}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>\\n' }}\n {%- elif loop.last %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '\\n\\n\\n\\n' }}\n {%- else %}\n {{- '\\n' }}\n {%- endif %}\n{%- endif %}\n{#- Unsloth fixes - developer role, tool calling #}",
"chat_template_caps": {
"supports_object_arguments": true,
"supports_parallel_tool_calls": true,
"supports_preserve_reasoning": true,
"supports_string_content": true,
"supports_system_role": true,
"supports_tool_calls": true,
"supports_tools": true,
"supports_typed_content": false
},
"bos_token": "<|endoftext|>",
"eos_token": "<|im_end|>",
"build_info": "b9418-2cbfdc62",
"is_sleeping": false
},
"interesting_lines": [
"0.00.113.705 I - CUDA0 : NVIDIA GeForce RTX 3090 Ti (24563 MiB, 23285 MiB free)",
"0.00.622.101 I llama_prepare_model_devices: using device CUDA0 (NVIDIA GeForce RTX 3090 Ti) (0000:0a:00.0) - 23285 MiB free",
"0.01.046.436 I load: special tokens cache size = 33",
"0.01.437.290 I load: token to piece cache size = 1.7581 MB",
"0.01.455.321 I load_tensors: CPU model buffer size = 0.00 MiB",
"0.01.455.322 I load_tensors: CUDA0 model buffer size = 0.00 MiB",
"0.01.467.402 I llama_context: CUDA_Host output buffer size = 2.84 MiB",
"0.01.475.668 I llama_kv_cache: CUDA0 KV buffer size = 0.00 MiB",
"0.01.512.217 I llama_memory_recurrent: CUDA0 RS buffer size = 1346.62 MiB",
"0.01.527.057 I sched_reserve: CUDA0 compute buffer size = 124.72 MiB",
"0.01.527.061 I sched_reserve: CUDA_Host compute buffer size = 36.54 MiB",
"0.01.528.300 I common_memory_breakdown_print: | - CUDA0 (RTX 3090 Ti) | 24563 = 21937 + (19241 = 13410 + 5706 + 124) + -16614 |",
"0.02.083.384 I llama_prepare_model_devices: using device CUDA0 (NVIDIA GeForce RTX 3090 Ti) (0000:0a:00.0) - 23285 MiB free",
"0.02.499.961 I load: special tokens cache size = 33",
"0.02.887.121 I load: token to piece cache size = 1.7581 MB",
"0.05.507.470 I load_tensors: CPU_Mapped model buffer size = 682.03 MiB",
"0.05.507.474 I load_tensors: CUDA0 model buffer size = 13410.41 MiB",
"0.10.154.860 I llama_context: CUDA_Host output buffer size = 2.84 MiB",
"0.10.169.845 I llama_kv_cache: CUDA0 KV buffer size = 4359.38 MiB",
"0.10.459.982 I llama_memory_recurrent: CUDA0 RS buffer size = 1346.62 MiB",
"0.10.481.902 I sched_reserve: CUDA0 compute buffer size = 124.72 MiB",
"0.10.481.906 I sched_reserve: CUDA_Host compute buffer size = 36.54 MiB",
"0.10.627.259 I llama_context: CUDA_Host output buffer size = 2.84 MiB",
"0.10.637.248 I llama_kv_cache: CUDA0 KV buffer size = 272.46 MiB",
"0.10.662.026 I sched_reserve: CUDA0 compute buffer size = 124.72 MiB",
"0.10.662.030 I sched_reserve: CUDA_Host compute buffer size = 36.54 MiB"
]
},
{
"name": "thetom-35a3b-q3xl-mtp-np3-192k",
"model": "C:\\Users\\sjake\\LLM\\models\\unsloth-qwen3.6-35b-a3b-mtp-gguf\\Qwen3.6-35B-A3B-UD-Q3_K_XL.gguf",
"mtp": true,
"log": "C:\\Users\\sjake\\LLM\\logs\\thetom-35a3b-q3xl-mtp-np3-192k-20260526-191235.loadonly.log",
"before": {
"used_mib": 1031,
"free_mib": 23283,
"power_w": 28.41,
"temp_c": 48
},
"ready": {
"used_mib": 19589,
"free_mib": 4725,
"power_w": 65.04,
"temp_c": 50
},
"stable": {
"used_mib": 19594,
"free_mib": 4720,
"power_w": 28.88,
"temp_c": 48
},
"net_ready_mib": 18558,
"props": {
"default_generation_settings": {
"params": {
"seed": 4294967295,
"temperature": 1.0,
"dynatemp_range": 0.0,
"dynatemp_exponent": 1.0,
"top_k": 20,
"top_p": 0.949999988079071,
"min_p": 0.05000000074505806,
"top_n_sigma": -1.0,
"xtc_probability": 0.0,
"xtc_threshold": 0.10000000149011612,
"typical_p": 1.0,
"repeat_last_n": 64,
"repeat_penalty": 1.0,
"presence_penalty": 0.0,
"frequency_penalty": 0.0,
"dry_multiplier": 0.0,
"dry_base": 1.75,
"dry_allowed_length": 2,
"dry_penalty_last_n": -1,
"mirostat": 0,
"mirostat_tau": 5.0,
"mirostat_eta": 0.10000000149011612,
"max_tokens": -1,
"n_predict": -1,
"n_keep": 0,
"n_discard": 0,
"ignore_eos": false,
"stream": true,
"n_probs": 0,
"min_keep": 0,
"chat_format": "Content-only",
"reasoning_format": "none",
"reasoning_in_content": false,
"generation_prompt": "",
"samplers": [
"penalties",
"dry",
"top_n_sigma",
"top_k",
"typ_p",
"top_p",
"min_p",
"xtc",
"temperature"
],
"speculative.types": "none",
"timings_per_token": false,
"post_sampling_probs": false,
"backend_sampling": false,
"lora": []
},
"n_ctx": 64000
},
"total_slots": 3,
"model_alias": "Qwen3.6-35B-A3B-UD-Q3_K_XL.gguf",
"model_path": "C:\\Users\\sjake\\LLM\\models\\unsloth-qwen3.6-35b-a3b-mtp-gguf\\Qwen3.6-35B-A3B-UD-Q3_K_XL.gguf",
"modalities": {
"vision": false,
"audio": false
},
"media_marker": "<__media_7aJPbvJaR34tnF14tqPrgU7WrZLcLK1r__>",
"endpoint_slots": true,
"endpoint_props": false,
"endpoint_metrics": false,
"ui": false,
"ui_settings": {},
"webui": false,
"webui_settings": {},
"chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n {%- if content is string %}\n {{- content }}\n {%- elif content is iterable and content is not mapping %}\n {%- for item in content %}\n {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain images.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Picture ' ~ image_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n {%- elif 'video' in item or item.type == 'video' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain videos.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Video ' ~ video_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- else %}\n {{- raise_exception('Unexpected item type in content.') }}\n {%- endif %}\n {%- endfor %}\n {%- elif content is none or content is undefined %}\n {{- '' }}\n {%- else %}\n {{- raise_exception('Unexpected content type.') }}\n {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- set num_sys = 0 %}\n{%- set merged_system = '' %}\n{%- if messages[0].role == 'system' or messages[0].role == 'developer' %}\n {%- set first = render_content(messages[0].content, false, true)|trim %}\n {%- if messages|length > 1 and (messages[1].role == 'system' or messages[1].role == 'developer') %}\n {%- set second = render_content(messages[1].content, false, true)|trim %}\n {%- set merged_system = first + '\\n' + second %}\n {%- set num_sys = 2 %}\n {%- else %}\n {%- set merged_system = first %}\n {%- set num_sys = 1 %}\n {%- endif %}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n {{- '<|im_start|>system\\n' }}\n {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n\" }}\n {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n\\n\\n\\nvalue_1\\n\\n\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n\\n\\n\\n\\n\\nReminder:\\n- Function calls MUST follow the specified format: an inner block must be nested within XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n' }}\n {%- if merged_system %}\n {{- '\\n\\n' + merged_system }}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n{%- else %}\n {%- if merged_system %}\n {{- '<|im_start|>system\\n' + merged_system + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" %}\n {%- set content = render_content(message.content, false)|trim %}\n {%- if not(content.startswith('') and content.endswith('')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if loop.index0 >= num_sys and message.role != \"system\" and message.role != \"developer\" %}\n {%- set content = render_content(message.content, true)|trim %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '' in content %}\n {%- set reasoning_content = content.split('')[0].rstrip('\\n').split('')[-1].lstrip('\\n') %}\n {%- set content = content.split('')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- set reasoning_content = reasoning_content|trim %}\n {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}\n {{- '<|im_start|>' + message.role + '\\n\\n' + reasoning_content + '\\n\\n\\n' + content }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {%- if loop.first %}\n {%- if content|trim %}\n {{- '\\n\\n\\n\\n' }}\n {%- else %}\n {{- '\\n\\n' }}\n {%- endif %}\n {%- else %}\n {{- '\\n\\n\\n' }}\n {%- endif %}\n {%- if tool_call.arguments is mapping %}\n {%- for args_name in tool_call.arguments %}\n {%- set args_value = tool_call.arguments[args_name] %}\n {{- '\\n' }}\n {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}\n {{- args_value }}\n {{- '\\n\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n\\n' }}\n {{- content }}\n {{- '\\n' }}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>\\n' }}\n {%- elif loop.last %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '\\n\\n\\n\\n' }}\n {%- else %}\n {{- '\\n' }}\n {%- endif %}\n{%- endif %}\n{#- Unsloth fixes - developer role, tool calling #}",
"chat_template_caps": {
"supports_object_arguments": true,
"supports_parallel_tool_calls": true,
"supports_preserve_reasoning": true,
"supports_string_content": true,
"supports_system_role": true,
"supports_tool_calls": true,
"supports_tools": true,
"supports_typed_content": false
},
"bos_token": "<|endoftext|>",
"eos_token": "<|im_end|>",
"build_info": "b9418-2cbfdc62",
"is_sleeping": false
},
"interesting_lines": [
"0.00.110.410 I - CUDA0 : NVIDIA GeForce RTX 3090 Ti (24563 MiB, 23285 MiB free)",
"0.00.609.316 I llama_prepare_model_devices: using device CUDA0 (NVIDIA GeForce RTX 3090 Ti) (0000:0a:00.0) - 23285 MiB free",
"0.01.037.079 I load: special tokens cache size = 33",
"0.01.426.295 I load: token to piece cache size = 1.7581 MB",
"0.01.441.897 I load_tensors: CUDA0 model buffer size = 0.00 MiB",
"0.01.441.898 I load_tensors: CUDA_Host model buffer size = 0.00 MiB",
"0.01.454.086 I llama_context: CUDA_Host output buffer size = 2.84 MiB",
"0.01.462.359 I llama_kv_cache: CUDA0 KV buffer size = 0.00 MiB",
"0.01.478.236 I llama_memory_recurrent: CUDA0 RS buffer size = 565.31 MiB",
"0.01.492.590 I sched_reserve: CUDA0 compute buffer size = 125.22 MiB",
"0.01.492.594 I sched_reserve: CUDA_Host compute buffer size = 33.51 MiB",
"0.01.493.839 I common_memory_breakdown_print: | - CUDA0 (RTX 3090 Ti) | 24563 = 22719 + (17956 = 15903 + 1927 + 125) + -16112 |",
"0.02.035.935 I llama_prepare_model_devices: using device CUDA0 (NVIDIA GeForce RTX 3090 Ti) (0000:0a:00.0) - 23285 MiB free",
"0.02.454.243 I load: special tokens cache size = 33",
"0.02.844.320 I load: token to piece cache size = 1.7581 MB",
"0.06.028.657 I load_tensors: CPU_Mapped model buffer size = 515.31 MiB",
"0.06.028.659 I load_tensors: CUDA0 model buffer size = 15903.70 MiB",
"0.11.853.955 I llama_context: CUDA_Host output buffer size = 2.84 MiB",
"0.11.865.042 I llama_kv_cache: CUDA0 KV buffer size = 1362.30 MiB",
"0.11.964.267 I llama_memory_recurrent: CUDA0 RS buffer size = 565.31 MiB",
"0.11.984.683 I sched_reserve: CUDA0 compute buffer size = 125.22 MiB",
"0.11.984.686 I sched_reserve: CUDA_Host compute buffer size = 33.51 MiB",
"0.12.174.976 I llama_context: CUDA_Host output buffer size = 2.84 MiB",
"0.12.184.236 I llama_kv_cache: CUDA0 KV buffer size = 136.23 MiB",
"0.12.201.197 I sched_reserve: CUDA0 compute buffer size = 124.21 MiB",
"0.12.201.201 I sched_reserve: CUDA_Host compute buffer size = 33.51 MiB"
]
},
{
"name": "thetom-35a3b-q3xl-nonmtp-np3-192k",
"model": "C:\\Users\\sjake\\LLM\\models\\unsloth-qwen3.6-35b-a3b-gguf\\Qwen3.6-35B-A3B-UD-Q3_K_XL.gguf",
"mtp": false,
"log": "C:\\Users\\sjake\\LLM\\logs\\thetom-35a3b-q3xl-nonmtp-np3-192k-20260526-191301.loadonly.log",
"before": {
"used_mib": 1030,
"free_mib": 23284,
"power_w": 28.32,
"temp_c": 47
},
"ready": {
"used_mib": 18573,
"free_mib": 5741,
"power_w": 83.54,
"temp_c": 50
},
"stable": {
"used_mib": 18578,
"free_mib": 5736,
"power_w": 30.06,
"temp_c": 48
},
"net_ready_mib": 17543,
"props": {
"default_generation_settings": {
"params": {
"seed": 4294967295,
"temperature": 1.0,
"dynatemp_range": 0.0,
"dynatemp_exponent": 1.0,
"top_k": 20,
"top_p": 0.949999988079071,
"min_p": 0.05000000074505806,
"top_n_sigma": -1.0,
"xtc_probability": 0.0,
"xtc_threshold": 0.10000000149011612,
"typical_p": 1.0,
"repeat_last_n": 64,
"repeat_penalty": 1.0,
"presence_penalty": 0.0,
"frequency_penalty": 0.0,
"dry_multiplier": 0.0,
"dry_base": 1.75,
"dry_allowed_length": 2,
"dry_penalty_last_n": -1,
"mirostat": 0,
"mirostat_tau": 5.0,
"mirostat_eta": 0.10000000149011612,
"max_tokens": -1,
"n_predict": -1,
"n_keep": 0,
"n_discard": 0,
"ignore_eos": false,
"stream": true,
"n_probs": 0,
"min_keep": 0,
"chat_format": "Content-only",
"reasoning_format": "none",
"reasoning_in_content": false,
"generation_prompt": "",
"samplers": [
"penalties",
"dry",
"top_n_sigma",
"top_k",
"typ_p",
"top_p",
"min_p",
"xtc",
"temperature"
],
"speculative.types": "none",
"timings_per_token": false,
"post_sampling_probs": false,
"backend_sampling": false,
"lora": []
},
"n_ctx": 64000
},
"total_slots": 3,
"model_alias": "Qwen3.6-35B-A3B-UD-Q3_K_XL.gguf",
"model_path": "C:\\Users\\sjake\\LLM\\models\\unsloth-qwen3.6-35b-a3b-gguf\\Qwen3.6-35B-A3B-UD-Q3_K_XL.gguf",
"modalities": {
"vision": false,
"audio": false
},
"media_marker": "<__media_oUVMr4APyWqChiyxfJoWT4gNPVmJ1Nqa__>",
"endpoint_slots": true,
"endpoint_props": false,
"endpoint_metrics": false,
"ui": false,
"ui_settings": {},
"webui": false,
"webui_settings": {},
"chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n {%- if content is string %}\n {{- content }}\n {%- elif content is iterable and content is not mapping %}\n {%- for item in content %}\n {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain images.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Picture ' ~ image_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n {%- elif 'video' in item or item.type == 'video' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain videos.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Video ' ~ video_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- else %}\n {{- raise_exception('Unexpected item type in content.') }}\n {%- endif %}\n {%- endfor %}\n {%- elif content is none or content is undefined %}\n {{- '' }}\n {%- else %}\n {{- raise_exception('Unexpected content type.') }}\n {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- set num_sys = 0 %}\n{%- set merged_system = '' %}\n{%- if messages[0].role == 'system' or messages[0].role == 'developer' %}\n {%- set first = render_content(messages[0].content, false, true)|trim %}\n {%- if messages|length > 1 and (messages[1].role == 'system' or messages[1].role == 'developer') %}\n {%- set second = render_content(messages[1].content, false, true)|trim %}\n {%- set merged_system = first + '\\n' + second %}\n {%- set num_sys = 2 %}\n {%- else %}\n {%- set merged_system = first %}\n {%- set num_sys = 1 %}\n {%- endif %}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n {{- '<|im_start|>system\\n' }}\n {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n\" }}\n {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n\\n\\n\\nvalue_1\\n\\n\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n\\n\\n\\n\\n\\nReminder:\\n- Function calls MUST follow the specified format: an inner block must be nested within XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n' }}\n {%- if merged_system %}\n {{- '\\n\\n' + merged_system }}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n{%- else %}\n {%- if merged_system %}\n {{- '<|im_start|>system\\n' + merged_system + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" %}\n {%- set content = render_content(message.content, false)|trim %}\n {%- if not(content.startswith('') and content.endswith('')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if loop.index0 >= num_sys and message.role != \"system\" and message.role != \"developer\" %}\n {%- set content = render_content(message.content, true)|trim %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '' in content %}\n {%- set reasoning_content = content.split('')[0].rstrip('\\n').split('')[-1].lstrip('\\n') %}\n {%- set content = content.split('')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- set reasoning_content = reasoning_content|trim %}\n {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}\n {{- '<|im_start|>' + message.role + '\\n\\n' + reasoning_content + '\\n\\n\\n' + content }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {%- if loop.first %}\n {%- if content|trim %}\n {{- '\\n\\n\\n\\n' }}\n {%- else %}\n {{- '\\n\\n' }}\n {%- endif %}\n {%- else %}\n {{- '\\n\\n\\n' }}\n {%- endif %}\n {%- if tool_call.arguments is mapping %}\n {%- for args_name in tool_call.arguments %}\n {%- set args_value = tool_call.arguments[args_name] %}\n {{- '\\n' }}\n {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}\n {{- args_value }}\n {{- '\\n\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n\\n' }}\n {{- content }}\n {{- '\\n' }}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>\\n' }}\n {%- elif loop.last %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '\\n\\n\\n\\n' }}\n {%- else %}\n {{- '\\n' }}\n {%- endif %}\n{%- endif %}\n{#- Unsloth fixes - developer role, tool calling #}",
"chat_template_caps": {
"supports_object_arguments": true,
"supports_parallel_tool_calls": true,
"supports_preserve_reasoning": true,
"supports_string_content": true,
"supports_system_role": true,
"supports_tool_calls": true,
"supports_tools": true,
"supports_typed_content": false
},
"bos_token": "<|endoftext|>",
"eos_token": "<|im_end|>",
"build_info": "b9418-2cbfdc62",
"is_sleeping": false
},
"interesting_lines": [
"0.00.110.474 I - CUDA0 : NVIDIA GeForce RTX 3090 Ti (24563 MiB, 23285 MiB free)",
"0.00.614.997 I llama_prepare_model_devices: using device CUDA0 (NVIDIA GeForce RTX 3090 Ti) (0000:0a:00.0) - 23285 MiB free",
"0.01.042.702 I load: special tokens cache size = 33",
"0.01.438.502 I load: token to piece cache size = 1.7581 MB",
"0.01.453.740 I load_tensors: CUDA0 model buffer size = 0.00 MiB",
"0.01.453.741 I load_tensors: CUDA_Host model buffer size = 0.00 MiB",
"0.01.466.137 I llama_context: CUDA_Host output buffer size = 2.84 MiB",
"0.01.474.356 I llama_kv_cache: CUDA0 KV buffer size = 0.00 MiB",
"0.01.480.261 I llama_memory_recurrent: CUDA0 RS buffer size = 188.44 MiB",
"0.01.494.824 I sched_reserve: CUDA0 compute buffer size = 125.22 MiB",
"0.01.494.828 I sched_reserve: CUDA_Host compute buffer size = 33.51 MiB",
"0.01.496.049 I common_memory_breakdown_print: | - CUDA0 (RTX 3090 Ti) | 24563 = 23095 + (17215 = 15539 + 1550 + 125) + -15746 |",
"0.02.035.945 I llama_prepare_model_devices: using device CUDA0 (NVIDIA GeForce RTX 3090 Ti) (0000:0a:00.0) - 23285 MiB free",
"0.02.448.988 I load: special tokens cache size = 33",
"0.02.836.125 I load: token to piece cache size = 1.7581 MB",
"0.05.716.756 I load_tensors: CPU_Mapped model buffer size = 515.31 MiB",
"0.05.716.758 I load_tensors: CUDA0 model buffer size = 15539.34 MiB",
"0.11.391.475 I llama_context: CUDA_Host output buffer size = 2.84 MiB",
"0.11.402.050 I llama_kv_cache: CUDA0 KV buffer size = 1362.30 MiB",
"0.11.478.868 I llama_memory_recurrent: CUDA0 RS buffer size = 188.44 MiB",
"0.11.499.989 I sched_reserve: CUDA0 compute buffer size = 125.22 MiB",
"0.11.499.994 I sched_reserve: CUDA_Host compute buffer size = 33.51 MiB"
]
}
]