Open-weight models that run on CPU only · 256 GB

256 GB DDR5 dual channel · 89.6 GB/s
Usable 250.0 GB

Search Precision Context Concurrent requests Minimum speed Architecture Type Maker Sort

Fit	Model	Parameters / active	Precision	Memory	Est. speed	Longest context	Runs as
Runs well	ERNIE-5.5-Flash-Base Baidu	286.2B	Q5_K_M	199.5 / 250.0 GB	speed not estimated	1024K	System memory
Runs well	Step 3.7 Flash StepFun	201.4B	Q4_K_M	121.0 / 250.0 GB	13–20 tok/s	250K	System memory
Runs well	Ling-3.0-flash Ant Group	127.5B / 5.1B	Q4_K_Mmaker’s file	75.7 / 250.0 GB	13–19 tok/s	250K	System memory
Runs well	Ling-3.0-flash-VL Ant Group	124.8B / 5.5B	Q4_0	69.0 / 250.0 GB	13–19 tok/s	128K	System memory
Runs well	gpt-oss-120b OpenAI	116.8B / 5.1B	MXFP4 (native)maker’s file	64.1 / 250.0 GB	14–21 tok/s	128K	System memory
Runs well	Qwen3-Next-80B-A3B-Instruct Alibaba Qwen	81.3B / 3B	Q8_0maker’s file	83.1 / 250.0 GB	13–20 tok/s	256K	System memory
Runs well	Qwen3-Next-80B-A3B-Thinking Alibaba Qwen	81.3B / 3B	Q8_0maker’s file	83.1 / 250.0 GB	13–20 tok/s	256K	System memory
Runs well	Qwen3-Coder-Next Alibaba Qwen	79.7B / 3B	Q8_0maker’s file	83.1 / 250.0 GB	13–20 tok/s	256K	System memory
Runs well	Qwen3.5-35B-A3B Alibaba Qwen	36B / 3B	Q8_0	37.5 / 250.0 GB	13–20 tok/s	256K	System memory
Runs well	Qwen3.6-35B-A3B Alibaba Qwen	36B / 3B	Q8_0	37.5 / 250.0 GB	13–20 tok/s	256K	System memory
Runs well	Qwen3-Omni-30B-A3B-Captioner Alibaba Qwen	31.7B	Q4_K_M	19.6 / 250.0 GB	13–19 tok/s	64K	System memory
Runs well	GLM-4.7-Flash Zhipu AI	31.2B	Q4_0	17.6 / 250.0 GB	13–20 tok/s	195K	System memory
Runs well	Qwen3-VL-30B-A3B-Instruct Alibaba Qwen	31.1B	Q5_K_M	22.4 / 250.0 GB	13–19 tok/s	128K	System memory
Runs well	Qwen3-VL-30B-A3B-Thinking Alibaba Qwen	31.1B	Q5_K_M	22.4 / 250.0 GB	13–19 tok/s	128K	System memory
Runs well	Qwen3-30B-A3B-Instruct-2507 Alibaba Qwen	30.5B / 3.3B	Q6_K	25.3 / 250.0 GB	13–19 tok/s	256K	System memory
Runs well	Qwen3-30B-A3B-Thinking-2507 Alibaba Qwen	30.5B / 3.3B	Q6_K	25.3 / 250.0 GB	13–19 tok/s	256K	System memory
Runs well	Qwen3-30B-A3B Alibaba Qwen	30.5B / 3.3B	Q6_Kmaker’s file	25.3 / 250.0 GB	13–19 tok/s	128K	System memory
Runs well	Qwen3-Coder-30B-A3B-Instruct Alibaba Qwen	30.5B / 3.3B	Q6_K	25.3 / 250.0 GB	13–19 tok/s	256K	System memory
Runs well	Hy-Memory-30B-A3B Tencent	30.1B / 3B	Q6_Kmaker’s file	24.9 / 250.0 GB	14–21 tok/s	63K	System memory
Runs well	Gemma 4 26B A4B IT Google	25.8B / 3.8B	Q5_K_M	18.5 / 250.0 GB	14–21 tok/s	250K	System memory
Runs well	ERNIE-4.5-21B-A3B-Thinking Baidu	21.8B / 3B	FP8	21.8 / 250.0 GB	13–19 tok/s	128K	System memory
Runs well	GPT OSS 20B OpenAI	20.9B / 3.6B	MXFP4 (native)maker’s file	13.6 / 250.0 GB	17–26 tok/s	128K	System memory
Runs well	Ling-3.0-tiny Ant Group	7.9B / 1.3B	BF16 (native)maker’s file	15.6 / 250.0 GB	16–24 tok/s	128K	System memory
Runs well	Gemma 4 E2B Google	5.1B	Q4_K_M	3.5 / 250.0 GB	14–21 tok/s	125K	System memory
Runs well	Qwen3.5-4B Alibaba Qwen	4.7B	Q5_K_M	3.8 / 250.0 GB	13–19 tok/s	256K	System memory
Runs well	Qwen3-VL-4B-Instruct Alibaba Qwen	4.4B	IQ4_XS	3.8 / 250.0 GB	13–19 tok/s	250K	System memory
Runs well	Qwen3-4B-Instruct-2507 Alibaba Qwen	4B	Q4_0	3.7 / 250.0 GB	13–19 tok/s	256K	System memory
Runs well	Qwen3-4B Alibaba Qwen	4B	Q4_0	3.7 / 250.0 GB	13–19 tok/s	128K	System memory
Runs well	DeepSeek-OCR DeepSeek	3.3B	BF16 (native)maker’s file	7.2 / 250.0 GB	16–24 tok/s	8K	System memory
Runs well	Granite-4.0-H-Micro IBM	3.2B	Q8_0maker’s file	3.7 / 250.0 GB	13–19 tok/s	128K	System memory
Runs well	Qwen3-1.7B Alibaba Qwen	2B	Q8_0maker’s file	3.1 / 250.0 GB	16–24 tok/s	40K	System memory
Runs well	DeepSeek-R1-Distill-Qwen-1.5B DeepSeek	1.8B	Q8_0	2.5 / 250.0 GB	21–32 tok/s	125K	System memory
Runs well	GLM-OCR Zhipu AI	1.3B	BF16 (native)maker’s file	3.5 / 250.0 GB	14–21 tok/s	128K	System memory
Runs well	Qwen3-0.6B Alibaba Qwen	0.8B	BF16 (native)maker’s file	2.8 / 250.0 GB	18–28 tok/s	40K	System memory
Runs well	EmbeddingGemma 2 Google	0.7B	BF16 (native)maker’s file	2.0 / 250.0 GB	28–43 tok/s	256K	System memory
Runs well	Qwen3-Embedding-0.6B Alibaba Qwen	0.6B	BF16 (native)maker’s file	2.5 / 250.0 GB	21–32 tok/s	32K	System memory
Runs well	bge-reranker-v2-m3 BAAI	0.6B	FP32 (native)maker’s file	3.4 / 250.0 GB	15–22 tok/s	8K	System memory
Runs well	bge-m3-unsupervised BAAI	0.6B	FP32 (native)maker’s file	3.4 / 250.0 GB	15–22 tok/s	8K	System memory
Runs well	bge-large-en-v1.5 BAAI	0.3B	FP32 (native)maker’s file	1.8 / 250.0 GB	32–48 tok/s	512	System memory
Runs well	bge-reranker-base BAAI	0.3B	FP32 (native)maker’s file	1.6 / 250.0 GB	40–59 tok/s	514	System memory
Runs well	bge-base-en-v1.5 BAAI	0.1B	FP32 (native)maker’s file	0.9 / 250.0 GB	98–147 tok/s	512	System memory
Runs well	bge-small-en-v1.5 BAAI	0B	FP32 (native)maker’s file	0.6 / 250.0 GB	313–470 tok/s	512	System memory
Runs, slowly	MiniMax-M3 MiniMax	427B / 23B	IQ4_XS	222.8 / 250.0 GB	3–5 tok/s	240K	System memory
Runs, slowly	Qwen3.5-397B-A17B Alibaba Qwen	403.4B / 17B	Q4_0	222.1 / 250.0 GB	5–7 tok/s	256K	System memory
Runs, slowly	GLM-4.5 Zhipu AI	358.3B	Q4_K_M	215.8 / 250.0 GB	2–2 tok/s	103K	System memory
Runs, slowly	GLM-4.7 Zhipu AI	358.3B	Q4_K_M	215.8 / 250.0 GB	2–2 tok/s	103K	System memory
Runs, slowly	GLM-4.6 Zhipu AI	356.8B	Q4_K_M	214.8 / 250.0 GB	2–3 tok/s	106K	System memory
Runs, slowly	GLM-5.3-Flash Zhipu AI	321.3B / 18B	Q5_K_M	223.8 / 250.0 GB	3–5 tok/s	603K	System memory
Runs, slowly	MiMo-V2.5 Xiaomi	310.8B / 15B	Q5_K_M	217.3 / 250.0 GB	4–6 tok/s	241K	System memory
Runs, slowly	DeepSeek-V4-Flash (2026-07-31) DeepSeek	304.2B	FP8 (native)maker’s file	163.9 / 250.0 GB	2–4 tok/s	977K	System memory
Runs, slowly	Hy3 Tencent	298.8B / 21B	Q5_K_M	210.3 / 250.0 GB	3–4 tok/s	135K	System memory
Runs, slowly	DeepSeek-V4-Flash (2026-04-24) DeepSeek	290.9B / 13B	FP8 (native)maker’s file	156.8 / 250.0 GB	6–9 tok/s	1024K	System memory
Runs, slowly	DeepSeek-V4-Flash DeepSeek	290.9B / 13B	FP8 (native)maker’s file	156.8 / 250.0 GB	6–9 tok/s	977K	System memory
Runs, slowly	Qwen3-VL-235B-A22B-Instruct Alibaba Qwen	235.7B	Q6_K	190.7 / 250.0 GB	2–3 tok/s	128K	System memory
Runs, slowly	Qwen3-VL-235B-A22B-Thinking Alibaba Qwen	235.7B	Q6_K	190.7 / 250.0 GB	2–3 tok/s	128K	System memory
Runs, slowly	Qwen3-235B-A22B-Instruct-2507 Alibaba Qwen	235.1B / 22B	Q6_K	190.3 / 250.0 GB	2–3 tok/s	256K	System memory
Runs, slowly	Qwen3-235B-A22B-Thinking-2507 Alibaba Qwen	235.1B / 22B	Q6_K	190.3 / 250.0 GB	2–3 tok/s	256K	System memory
Runs, slowly	Qwen3-235B-A22B Alibaba Qwen	235.1B / 22B	Q6_Kmaker’s file	190.2 / 250.0 GB	2–3 tok/s	128K	System memory
Runs, slowly	MiniMax-M2.1 MiniMax	228.7B	Q6_K	185.6 / 250.0 GB	4–6 tok/s	192K	System memory
Runs, slowly	MiniMax-M2.5 MiniMax	228.7B	Q6_K	185.6 / 250.0 GB	4–6 tok/s	192K	System memory
Runs, slowly	MiniMax-M2.7 MiniMax	228.7B	Q6_K	185.6 / 250.0 GB	4–6 tok/s	200K	System memory
Runs, slowly	MiniMax-M2 MiniMax	228.7B / 10B	Q6_K	185.6 / 250.0 GB	4–7 tok/s	192K	System memory
Runs, slowly	MiniMax-M3.1-Flash MiniMax	220.5B / 23B	FP8	216.6 / 250.0 GB	2–3 tok/s	293K	System memory
Runs, slowly	Step 3.5 Flash StepFun	199.4B / 11B	Q8_0	208.6 / 250.0 GB	3–5 tok/s	244K	System memory
Runs, slowly	Ming-3.0-audio-flash Ant Group	128.2B / 6.5B	Q8_0	133.6 / 250.0 GB	6–9 tok/s	128K	System memory
Runs, slowly	Qwen3.5-122B-A10B Alibaba Qwen	125.1B / 10B	Q8_0	130.2 / 250.0 GB	4–6 tok/s	256K	System memory
Runs, slowly	GLM-4.5-Air Zhipu AI	110.5B	BF16 (native)maker’s file	217.5 / 250.0 GB	1–2 tok/s	125K	System memory
Runs, slowly	GLM-4.5V Zhipu AI	107.7B / 12B	BF16 (native)maker’s file	212.1 / 250.0 GB	2–3 tok/s	63K	System memory
Runs, slowly	GLM-4.6V Zhipu AI	107.7B	BF16 (native)maker’s file	212.1 / 250.0 GB	1–2 tok/s	125K	System memory
Runs, slowly	Ling-2.6-flash Ant Group	107.5B / 7.4B	BF16 (native)maker’s file	210.5 / 250.0 GB	3–4 tok/s	128K	System memory
Runs, slowly	Qwen2.5-VL-72B-Instruct Alibaba Qwen	73.4B	BF16 (native)maker’s file	146.1 / 250.0 GB	0–0 tok/s	125K	System memory
Runs, slowly	Qwen2-VL-72B-Instruct Alibaba Qwen	73.4B	BF16 (native)maker’s file	146.1 / 250.0 GB	0–0 tok/s	32K	System memory
Runs, slowly	Qwen2.5-72B-Instruct Alibaba Qwen	72.7B	BF16 (native)maker’s file	144.7 / 250.0 GB	0–0 tok/s	32K	System memory
Runs, slowly	Qianfan-VL-70B Baidu	71.8B	BF16 (native)maker’s file	143.0 / 250.0 GB	0–0 tok/s	32K	System memory
Runs, slowly	DeepSeek-R1-Distill-Llama-70B DeepSeek	70.6B	BF16 (native)maker’s file	140.5 / 250.0 GB	0–0 tok/s	125K	System memory
Runs, slowly	Qwen2.5-VL-32B-Instruct Alibaba Qwen	33.5B	BF16 (native)maker’s file	68.8 / 250.0 GB	1–1 tok/s	125K	System memory
Runs, slowly	Qwen3-VL-32B-Instruct Alibaba Qwen	33.4B	BF16 (native)maker’s file	67.2 / 250.0 GB	1–1 tok/s	128K	System memory
Runs, slowly	Qwen3-VL-32B-Thinking Alibaba Qwen	33.4B	BF16 (native)maker’s file	67.2 / 250.0 GB	1–1 tok/s	128K	System memory
Runs, slowly	Qwen2.5-32B-Instruct Alibaba Qwen	32.8B	BF16 (native)maker’s file	66.1 / 250.0 GB	1–1 tok/s	32K	System memory
Runs, slowly	Qwen2.5-Coder-32B-Instruct Alibaba Qwen	32.8B	BF16 (native)maker’s file	66.1 / 250.0 GB	1–1 tok/s	32K	System memory
Runs, slowly	QwQ-32B Alibaba Qwen	32.8B	BF16 (native)maker’s file	66.1 / 250.0 GB	1–1 tok/s	40K	System memory
Runs, slowly	DeepSeek-R1-Distill-Qwen-32B DeepSeek	32.8B	BF16 (native)maker’s file	66.1 / 250.0 GB	1–1 tok/s	32K	System memory
Runs, slowly	Qwen3-32B Alibaba Qwen	32.8B	BF16 (native)maker’s file	66.1 / 250.0 GB	1–1 tok/s	128K	System memory
Runs, slowly	Gemma 4 31B IT Google	31.3B	BF16 (native)maker’s file	63.2 / 250.0 GB	1–1 tok/s	250K	System memory
Runs, slowly	Granite Switch 4.1 30B IBM	30B	BF16 (native)maker’s file	60.7 / 250.0 GB	1–1 tok/s	128K	System memory
Runs, slowly	Qwen3.5-27B Alibaba Qwen	27.8B	BF16 (native)maker’s file	54.8 / 250.0 GB	1–1 tok/s	256K	System memory
Runs, slowly	Qwen3.6-27B Alibaba Qwen	27.8B	BF16 (native)maker’s file	54.8 / 250.0 GB	1–1 tok/s	256K	System memory
Runs, slowly	Qwen3.8-27B Alibaba Qwen	27.8B	BF16 (native)maker’s file	54.8 / 250.0 GB	1–1 tok/s	256K	System memory
Runs, slowly	Magistral Small 1.2 Mistral AI	24B	BF16 (native)maker’s file	95.2 / 250.0 GB	0–1 tok/s	125K	System memory
Runs, slowly	Devstral Small 1.0 Mistral AI	23.6B	BF16 (native)maker’s file	93.5 / 250.0 GB	0–1 tok/s	125K	System memory
Runs, slowly	Devstral Small 1.1 Mistral AI	23.6B	BF16 (native)maker’s file	93.5 / 250.0 GB	0–1 tok/s	125K	System memory
Runs, slowly	Magistral Small 1.0 Mistral AI	23.6B	BF16 (native)maker’s file	93.5 / 250.0 GB	0–1 tok/s	39K	System memory
Runs, slowly	Magistral Small 1.1 Mistral AI	23.6B	BF16 (native)maker’s file	93.5 / 250.0 GB	0–1 tok/s	39K	System memory
Runs, slowly	Qwen2.5-14B-Instruct-1M Alibaba Qwen	14.8B	BF16 (native)maker’s file	30.4 / 250.0 GB	1–2 tok/s	977K	System memory
Runs, slowly	Qwen2.5-14B-Instruct Alibaba Qwen	14.8B	BF16 (native)maker’s file	30.4 / 250.0 GB	1–2 tok/s	32K	System memory
Runs, slowly	DeepSeek-R1-Distill-Qwen-14B DeepSeek	14.8B	BF16 (native)maker’s file	30.4 / 250.0 GB	1–2 tok/s	32K	System memory
Runs, slowly	Qwen3-14B Alibaba Qwen	14.8B	BF16 (native)maker’s file	30.1 / 250.0 GB	1–2 tok/s	128K	System memory
Runs, slowly	Gemma 3 12B IT Google	12.2B	BF16 (native)maker’s file	26.6 / 250.0 GB	2–2 tok/s	128K	System memory
Runs, slowly	Qwen2.5-Omni-7B Alibaba Qwen	10.7B	BF16 (native)maker’s file	22.3 / 250.0 GB	2–3 tok/s	32K	System memory
Runs, slowly	GLM-4.6V-Flash Zhipu AI	10.3B	BF16 (native)maker’s file	20.4 / 250.0 GB	2–3 tok/s	125K	System memory
Runs, slowly	Qwen3.5-9B Alibaba Qwen	9.7B	BF16 (native)maker’s file	19.1 / 250.0 GB	2–3 tok/s	256K	System memory
Runs, slowly	Qianfan-VL-8B Baidu	8.8B	BF16 (native)maker’s file	18.2 / 250.0 GB	2–4 tok/s	32K	System memory
Runs, slowly	Granite Switch 4.1 8B IBM	8.8B	BF16 (native)maker’s file	18.5 / 250.0 GB	2–4 tok/s	128K	System memory
Runs, slowly	Qwen3-VL-8B-Instruct Alibaba Qwen	8.8B	BF16 (native)maker’s file	18.3 / 250.0 GB	2–4 tok/s	128K	System memory
Runs, slowly	Qwen3-VL-8B-Thinking Alibaba Qwen	8.8B	BF16 (native)maker’s file	18.3 / 250.0 GB	2–4 tok/s	128K	System memory
Runs, slowly	pplx-embed-v2-context-9b Perplexity	8.4B	FP32 (native)maker’s file	33.1 / 250.0 GB	1–2 tok/s	256K	System memory
Runs, slowly	Qwen2.5-VL-7B-Instruct Alibaba Qwen	8.3B	BF16 (native)maker’s file	16.7 / 250.0 GB	3–4 tok/s	125K	System memory
Runs, slowly	Qwen3-8B Alibaba Qwen	8.2B	BF16 (native)maker’s file	17.1 / 250.0 GB	3–4 tok/s	128K	System memory
Runs, slowly	DeepSeek-R1-Distill-Llama-8B DeepSeek	8B	BF16 (native)maker’s file	16.7 / 250.0 GB	3–4 tok/s	125K	System memory
Runs, slowly	Gemma 4 E4B Google	8B	BF16 (native)maker’s file	15.8 / 250.0 GB	3–4 tok/s	125K	System memory
Runs, slowly	Qwen2.5-7B-Instruct-1M Alibaba Qwen	7.6B	BF16 (native)maker’s file	15.3 / 250.0 GB	3–4 tok/s	977K	System memory
Runs, slowly	Qwen2.5-7B-Instruct Alibaba Qwen	7.6B	BF16 (native)maker’s file	15.3 / 250.0 GB	3–4 tok/s	32K	System memory
Runs, slowly	DeepSeek-R1-Distill-Qwen-7B DeepSeek	7.6B	BF16 (native)maker’s file	15.3 / 250.0 GB	3–4 tok/s	32K	System memory
Runs, slowly	Mistral-7B-Instruct-v0.1 Mistral AI	7.2B	BF16 (native)maker’s file	15.2 / 250.0 GB	3–4 tok/s	32K	System memory
Runs, slowly	WeVisOne-VL-4B Tencent	4.8B	BF16 (native)maker’s file	10.6 / 250.0 GB	4–6 tok/s	256K	System memory
Runs, slowly	Qianfan-OCR Baidu	4.7B	BF16 (native)maker’s file	10.5 / 250.0 GB	4–6 tok/s	31K	System memory

Estimates from the makers’ Hugging Face repositories (as of 2026-11-06); filtered views aren’t indexed. How it’s estimated