开源模型

体验记录

Qwen

模型标签评价
Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distill-heretic-v3.i1-Q4_K_M.ggufEnglish heretic abliteration uncensored imatrix conversationalopus 4B 体验还不错,照样能打
qwen3.5-4b-python-coder-q4_k_m.gguf 虽然是coder模型,continue补全返回总是空
Huihui-Qwen3.5-9B-Claude-4.6-Opus-abliterated-heretic.i1-Q4_K_S.ggufEnglish abliterated uncensored Claude reasoning chain-of-thought Dense heretic decensored imatrix conversationalchat没有任何问题
opencode+omo: Cannot determine type of 'item'
Qwen3.5-9B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING.i1-Q5_K_M.ggufEnglish Chinese fine tune creative creative writing fiction writing plot generation sub-plot generation story generation scene continue storytelling fiction story science fiction romance all genres story writing vivid prosing vivid writing fiction roleplaying bfloat16 all use cases unsloth heretic uncensored abliterated imatrix conversationalopencode+omo: Cannot determine type of 'item'
Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated-Q4_K_M.gguf  
Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-heretic.i1-Q6_K.gguf 功能交互正常,很能打
Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-GGUF  
Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated.i1-Q4_K_S.gguf 有丢失逻辑的感觉
Qwen3.5-35B-A3B-heretic-Opus-4.6-Distilled.i1-Q5_K_M.gguf 存在prefill is incompatible问题
Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled.i1-Q5_K_M.gguf 存在prefill is incompatible问题
Qwen3.6-35B-A3B-Abliterated-Heretic-Q4_K_M.gguf 存在prefill is incompatible问题,有时候编程任务计算返回空
Qwen3.6-35B-A3B-Opus-Q4_K_S.gguf  
rico03/Qwen3.6-35B-Opus-Reasoning-GGU  
hesamation/Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled.Q4_K_M.gguf  

Gemma

模型标签评价
gemma-4-E4b-it.Q4_K_M.gguf opencode有unused24问题,训练2025年1月
opencode+omo: Cannot determine type of 'item'
gemma-4-E2B-abliterated-btx-Q4_K_M.gguf 感觉很一般
SuperGemma4-31b-abliterated.Q4_K_M.gguf  
gemma-4-31B-it-Claude-Opus-Distill.q4_k_m.gguf’  
   

Llama

模型标签评价
llama4-dolphin-8b.q4_k_m.gguf 没啥感受
Llama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning.i1-Q4_K_S 10 languages thinking reasoning instruct heretic uncensored abliterated Claude4.5-Opus creative creative writing fiction writing plot generation sub-plot generation story generation scene continue storytelling fiction story science fiction romance all genres story writing vivid prosing vivid writing fiction roleplaying bfloat16 role play 128k context llama3.3 llama-3 llama-3.3 unsloth finetune imatrix conversationalopencode+omo: Cannot determine type of 'item'

Nemotron

模型标签评价
Nemotron-9B-OpenCode.i1-Q4_K_M.ggufEnglish Chinese code instruction-tuned software-engineering agent opencode qwen python imatrix conversationalopencode+omo: Cannot determine type of 'item'

其它

模型标签评价
nomic-embed-text-v1.5-Q8_0.gguf 没啥存在感

模型仓库

抱脸			https://huggingface.co/						美国AI初创公司
魔塔社区		https://modelscope.cn/models				阿里达摩院
鹏城实验室	https://openi.pcl.ac.cn/modelbase/list		深圳科技部
飞桨			https://aistudio.baidu.com/modelsoverview	百度
硅基流动		https://siliconflow.cn/models				OneFlow袁进辉
卡格尔		https://www.kaggle.com/models				Google

开源模型

Grok		Grok-2.5(314B MoE)		xAI(马斯克)	打破闭源实时能力垄断,倒逼 Meta/Google 加速开源
Llama		Llama 4-405B(多模态)	Meta		原生多模态,开源生态最广,开发者首选基座
Mistral		Mistral Small 4(22B)	Mistral AI	推理速度碾压同级,边缘部署首选,重塑轻量开源标准
Gemma		Gemma 4(E2B MoE)		Google		E2B仅1.5GB可手机离线跑,24小时下载破4 亿
Phi			Phi-4(14B/38B)			Microsoft	小参数强推理,14B版数学/代码超Llama3-70B
DBRX		DBRX-132B(MoE)			Databricks	首个开源MoE基座,代码/SQL能力登顶,推动开源MoE普及
Nemotron	Nemotron-4 340B			NVIDIA		NVIDIA官方开源旗舰,绑定CUDA生态,企业级部署首选
OLMo		OLMo-2-7B/13B			Allen		无商用限制,科研界标杆,推动 AI 透明化研究
Qwen		Qwen3.5-397B(MoE)		阿里通义		LM Arena盲测国产第一、全球第五,中文能力碾压
DeepSeek	DeepSeek-V3.2			深度求索		全面用海光/寒武纪国产芯片训练,脱离CUDA,成本降 60%
GLM			GLM-5.1(754B)			智谱 AI		SWE-bench Pro 国产第一、全球第三
InternLM	InternLM3-102B			上海商汤/浪潮	开源工具调用增强版,国产芯片友好,书生・浦语生态核心