评测了qwen3.8-27B 3个不同的社区版本(3bit - 4bit量化)以鹈鹕、北极熊为例。

996 2026-08-19 01:28 1

一、本人硬件:


RTX3090 24G + DDR5 32G + i5-14600K


二、测评模型:


1、unsloth/Qwen3.8-27B-GGUF/Qwen3.8-27B-Q4_K_M.gguf

(一个4bit量化版本,unsloth团队的量化质量极高。)


2、JonathanColetti/Qwen3.8-27B-Uncensored-GGUF/Qwen3.8-27B-Uncensored-Q4_K_M.gguf

(一个未审查4bit量化版本,社区热度极高)


3、zerodigest/Qwen3.8-27B-Uncensored-YMQ-MTP-GGUF/Qwen3.8-27B-Uncensored-YMQ-M.gguf

(一个未审查3bit量化版本,该作者声称此3bit能达到4bit的水准。)


三、思考程度:


qwen3.8-27B默认采用xhigh的思考程度导致思考链特别长,本次测试同时测评medium(中等)思考程度。


四、实际效果


1、鹈鹕骑自行车(一句话生成,不依赖任何智能体,通过直接对话聊天的方式)


提示词:创建一个HTML,内容是SVG绘制一个鹈鹕骑自行车的2D动画


(后面标写medium代表中等思考,没有标写代表默认xhigh思考)


(1)Qwen3.8-27B-Q4_K_M.gguf


(2)Qwen3.8-27B-Q4_K_M.gguf-medium


(3)Qwen3.8-27B-Uncensored-Q4_K_M.gguf-medium


(4)Qwen3.8-27B-Uncensored-YMQ-M.gguf


(5)Deepseek-v4-flash(来自opencode)


2、鹈鹕骑自行车 - pi (在 pi 智能体cli里输入一句话生成)


提示词:创建一个HTML,内容是SVG绘制一个鹈鹕骑自行车的2D动画


Qwen3.8-27B-Q4_K_M.gguf 时间关系,不测xhigh了,前面一句话生成就很完美了。


(1)Qwen3.8-27B-Q4_K_M.gguf-medium


(2)Qwen3.8-27B-Uncensored-Q4_K_M.gguf


(3)Qwen3.8-27B-Uncensored-Q4_K_M.gguf-medium


(4)Qwen3.8-27B-Uncensored-YMQ-M.gguf


(5)Qwen3.8-27B-Uncensored-YMQ-M.gguf-medium


3、秦始皇骑北极熊 - pi (在 pi 智能体cli里输入一句话生成)


提示词:创建一个HTML,内容是SVG绘制一个秦始皇骑北极熊的2D动画


(1)Qwen3.8-27B-Q4_K_M.gguf-medium


(2)Qwen3.8-27B-Uncensored-Q4_K_M.gguf


(3)Qwen3.8-27B-Uncensored-Q4_K_M.gguf-medium



(gif上传失败,只能截图,动画非常自然,甚至比xhigh好)


(4)Qwen3.8-27B-Uncensored-YMQ-M.gguf


(5)Qwen3.8-27B-Uncensored-YMQ-M.gguf-medium


五、本人启动参数


medium 中等思考:


~/llama.cpp/build/bin/llama-server \
-m /root/models/Qwen3.8-27B-Uncensored-YMQ-M.gguf \
--mmproj /root/models/mmproj-F16.gguf \
-ngl 99 \
-ctk q8_0 -ctv q4_1 \
--spec-type draft-mtp --spec-draft-n-max 2 \
--reasoning-preserve \
-np 2 \
-c 150000 --jinja -fa on \
--chat-template-file /root/models/unsloth/Qwen3.8-27B-GGUF/chat_template_qwen38_medium.jinja \
--host 0.0.0.0 \
--port 49444

其中chat_template_qwen38_medium.jinja:


{%- set image_count = namespace(value=0) %}
{%- set video_count = namespace(value=0) %}
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
{%- if content is string %}
{{- content }}
{%- elif content is iterable and content is not mapping %}
{%- for item in content %}
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
{%- if is_system_content %}
{{- raise_exception('System message cannot contain images.') }}
{%- endif %}
{%- if do_vision_count %}
{%- set image_count.value = image_count.value + 1 %}
{%- endif %}
{%- if add_vision_id %}
{{- 'Picture ' ~ image_count.value ~ ': ' }}
{%- endif %}
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
{%- elif 'video' in item or item.type == 'video' %}
{%- if is_system_content %}
{{- raise_exception('System message cannot contain videos.') }}
{%- endif %}
{%- if do_vision_count %}
{%- set video_count.value = video_count.value + 1 %}
{%- endif %}
{%- if add_vision_id %}
{{- 'Video ' ~ video_count.value ~ ': ' }}
{%- endif %}
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
{%- elif 'text' in item %}
{{- item.text }}
{%- else %}
{{- raise_exception('Unexpected item type in content.') }}
{%- endif %}
{%- endfor %}
{%- elif content is none or content is undefined %}
{{- '' }}
{%- else %}
{{- raise_exception('Unexpected content type.') }}
{%- endif %}
{%- endmacro %}
{%- if not messages %}
{{- raise_exception('No messages provided.') }}
{%- endif %}
{%- set sysns = namespace(count=0, text='') %}
{%- for message in messages %}
{%- if sysns.count == loop.index0 and (message.role == 'system' or message.role == 'developer') %}
{%- set sys_content = render_content(message.content, false, true)|trim %}
{%- if sys_content %}
{%- set sysns.text = sysns.text + ('\n' if sysns.text else '') + sys_content %}
{%- endif %}
{%- set sysns.count = sysns.count + 1 %}
{%- endif %}
{%- endfor %}
{%- set num_sys = sysns.count %}
{%- set merged_system = sysns.text %}
{%- set reasoning_instructions = '' %}
{%- if enable_thinking is undefined or enable_thinking is true %}
{%- set resolved_reasoning_effort = reasoning_effort|default('medium') %}
{%- if resolved_reasoning_effort == 'high' %}
{%- set resolved_reasoning_effort = 'xhigh' %}
{%- endif %}
{%- if resolved_reasoning_effort not in ('xhigh', 'medium', 'low') %}
{{- raise_exception('Unexpected reasoning effort ' ~ reasoning_effort ~ '. Supported types are xhigh (default), medium, and low.') }}
{%- endif %}
{%- if resolved_reasoning_effort == 'xhigh' %}
{%- set reasoning_instructions = 'Reasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.' %}
{%- elif resolved_reasoning_effort == 'low' %}
{%- set reasoning_instructions = 'Reasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.' %}
{%- endif %}
{%- endif %}
{%- if tools and tools is iterable and tools is not mapping %}
{{- '<|im_start|>system\n' }}
{%- if reasoning_instructions %}
{{- reasoning_instructions + '\n\n' }}
{%- endif %}
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\n</tools>" }}
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> 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</IMPORTANT>' }}
{%- if merged_system %}
{{- '\n\n' + merged_system }}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- else %}
{%- if merged_system %}
{{- '<|im_start|>system\n' + (reasoning_instructions + '\n\n' if reasoning_instructions else '') + merged_system + '<|im_end|>\n' }}
{%- elif reasoning_instructions %}
{{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
{%- for message in messages[::-1] %}
{%- set index = (messages|length - 1) - loop.index0 %}
{%- if ns.multi_step_tool and message.role == "user" %}
{%- set content = render_content(message.content, false)|trim %}
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
{%- set ns.multi_step_tool = false %}
{%- set ns.last_query_index = index %}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- for message in messages %}
{%- if loop.index0 >= num_sys %}
{%- set content = render_content(message.content, true)|trim %}
{%- if message.role == "system" or message.role == "developer" %}
{{- raise_exception('System message must be at the beginning.') }}
{%- elif message.role == "user" %}
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{%- set reasoning_content = '' %}
{%- if message.reasoning_content is string %}
{%- set reasoning_content = message.reasoning_content %}
{%- endif %}
{%- set reasoning_content = reasoning_content|trim %}
{%- if preserve_thinking is undefined or preserve_thinking is true or loop.index0 > ns.last_query_index %}
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
{%- for tool_call in message.tool_calls %}
{%- if tool_call.function is defined %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{%- if tool_call.name is not defined or tool_call.name is none %}
{{- raise_exception('Tool call is missing a function name.') }}
{%- endif %}
{%- if loop.first %}
{%- if content|trim %}
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
{%- else %}
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
{%- endif %}
{%- else %}
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
{%- endif %}
{%- if tool_call.arguments is mapping %}
{%- for args_name, args_value in tool_call.arguments|items %}
{{- '<parameter=' + args_name + '>\n' }}
{%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
{{- args_value }}
{{- '\n</parameter>\n' }}
{%- endfor %}
{%- elif tool_call.arguments is string %}
{%- if tool_call.arguments|trim %}
{{- raise_exception('Tool call arguments for function "' + (tool_call.name | string) + '" were passed as a JSON string. Parse them into an object before calling apply_chat_template.') }}
{%- endif %}
{%- elif tool_call.arguments is defined and tool_call.arguments is not none %}
{{- raise_exception('Tool call arguments for function "' + (tool_call.name | string) + '" must be an object/mapping or a JSON string.') }}
{%- endif %}
{{- '</function>\n</tool_call>' }}
{%- endfor %}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if loop.previtem and loop.previtem.role != "tool" %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '\n<tool_response>\n' }}
{{- content }}
{{- '\n</tool_response>' }}
{%- if not loop.last and loop.nextitem.role != "tool" %}
{{- '<|im_end|>\n' }}
{%- elif loop.last %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- else %}
{{- raise_exception('Unexpected message role.') }}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- if enable_thinking is defined and enable_thinking is false %}
{{- '<think>\n\n</think>\n\n' }}
{%- else %}
{{- '<think>\n' }}
{%- endif %}
{%- endif %}
{#- Unsloth fixes - developer role, merged system messages, tool calling #}


六、最终结论(不是很严谨,仅参考)


三模型对比:


1、xhigh模式下,Qwen3.8-27B-Q4_K_M最优。


2、medium模式下,Qwen3.8-27B-Uncensored-Q4_K_M最优,Qwen3.8-27B-Uncensored-YMQ-M.gguf次之。


3、在pi智能体里,Qwen3.8-27B-Uncensored-YMQ-M.gguf这个3bit模型也能达到不错的效果

最新回复 (2)
  • 996 楼主 08-19 01:39
    2

    确实变量控制的不是很严谨,只是跑了个大概的感觉,仅供大家参考。


    因为本地思考太长了,导致我50t/s左右也要等很久很久,所以跑完用了2-3小时。

  • kanadekiss 08-19 17:31
    3

    楼主用的什么 Harness 呢?我用的 dsh 搭配 q5_K_M 也是差不多效果 不过我看有说用 grok build 效果会更佳^-^

* 帖子来源Linux.do
返回