What LLMs can a GeForce RTX 3070 run?

Your rig

GeForce RTX 3070 · 8 GB

16 GB system RAM · Ampere · 448 GB/s · 7.0 GB usable VRAM

Which one should I actually run?

Best models for your GeForce RTX 3070

Updated 21 Aug 2026 5 new this week, 14 this month

What do you want to do? Each row is the best-ranked model on that use case's shortlist that fits at Q6_K and 4K. The ordering is editorial; the sizes and speeds are computed. How the shortlists work.

All General assistant Coding Reasoning & maths Writing Vision Agents & tool use Translation Low latency Long context

Recommendation	Model	Why	Quant · total	Tok/s est.
Best overall	Qwen3.5 4B Alibaba · Apache 2.0	The 6–8 GB pick: a real assistant in 3.4 GB of weights.	Q6_K · 4.3 GB	76	Runs great Run
Best for coding	Qwen3.5 4B Alibaba · Apache 2.0	A coding agent in 3.4 GB — the 6–8 GB answer.	Q6_K · 4.3 GB	76	Runs great Run
Best reasoning	Qwen3.5 4B Alibaba · Apache 2.0	Step-by-step reasoning in 8 GB.	Q6_K · 4.3 GB	76	Runs great Run
Best for writing	Qwen3.5 4B Alibaba · Apache 2.0	Competent drafting in 8 GB.	Q6_K · 4.3 GB	76	Runs great Run
Best vision	Qwen3.5 4B Alibaba · Apache 2.0	Reads screenshots in 8 GB.	Q6_K · 4.3 GB	76	Runs great Run
Best for agents	Qwen3.5 4B Alibaba · Apache 2.0	Function calling in 8 GB.	Q6_K · 4.3 GB	76	Runs great Run
Best translation	Qwen3.5 4B Alibaba · Apache 2.0	Usable translation in 8 GB.	Q6_K · 4.3 GB	76	Runs great Run
Fastest good model	Ling 3.0 Tiny 7.9B-A1.3B New inclusionAI · MIT	1.3B active with a latent cache on 6 of 24 layers.	Q6_K · 6.7 GB	105	Tight fit Run
Best long context	Qwen3.5 2B Alibaba · Apache 2.0	Long documents on 4 GB.	Q6_K · 3.8 GB at 128K context	156	Runs great Run

Everything that fits

Runs great

15 of 76 · fits with headroom for a longer prompt

Model	Params	Quant	Weights	+KV 4K	Total	VRAM headroom	Tok/s	Runtime
Gemma 4 E2B	5.1B	Q6_K	3.9 GB	0.04 GB	4.5 GB	2.5 GB free	70	Ollama	Run
Qwen3.5 4B	4.66B	Q6_K	3.6 GB	0.13 GB	4.3 GB	2.7 GB free	76	Ollama	Run
Gemma 3 4B	4.3B	Q6_K	3.3 GB	0.20 GB	4.1 GB	2.9 GB free	83	Ollama	Run
Qwen3 4B	4.02B	Q6_K	3.1 GB	0.56 GB	4.2 GB	2.8 GB free	88	Ollama	Run
Ministral 3 3B	3.85B	Q6_K	2.9 GB	0.41 GB	3.9 GB	3.1 GB free	92	Ollama	Run
Phi-4-mini 3.8B	3.84B	Q6_K	2.9 GB	0.50 GB	4.0 GB	3.0 GB free	92	Ollama	Run
Granite 4.1 3B	3.4B	Q6_K	2.6 GB	0.31 GB	3.5 GB	3.5 GB free	104	Ollama	Run
Llama 3.2 3B Instruct	3.21B	Q6_K	2.5 GB	0.44 GB	3.5 GB	3.5 GB free	111	Ollama	Run
LFM2.5 2.6B New	2.7B	Q6_K	2.1 GB	0.06 GB	2.7 GB	4.3 GB free	132	llama.cpp	Run
Qwen3.5 2B	2.27B	Q6_K	1.7 GB	0.05 GB	2.4 GB	4.6 GB free	156	Ollama	Run
Qwen3 1.7B	1.72B	Q6_K	1.3 GB	0.44 GB	2.4 GB	4.6 GB free	206	Ollama	Run
Llama 3.2 1B Instruct	1.24B	Q6_K	0.9 GB	0.13 GB	1.7 GB	5.3 GB free	286	Ollama	Run
Gemma 3 1B	1.0B	Q6_K	0.8 GB	0.03 GB	1.4 GB	5.6 GB free	355	Ollama	Run
Qwen3.5 0.8B	0.87B	Q6_K	0.7 GB	0.05 GB	1.3 GB	5.7 GB free	408	Ollama	Run
Qwen3 0.6B	0.6B	Q6_K	0.5 GB	0.44 GB	1.5 GB	5.5 GB free	592	Ollama	Run

Runs — tight

5 models · fits at 4K, drop context or quant to go longer

Model	Params	Quant	Weights	+KV 4K	Total	VRAM headroom	Tok/s	Runtime
Gemma 4 E4B	8.0B	Q6_K	6.1 GB	0.09 GB	6.8 GB	0.2 GB free	44	llama.cpp	Run
Ling 3.0 Tiny 7.9B-A1.3B New	7.9B MoE / 1.3B act	Q6_K	6.0 GB	0.03 GB	6.7 GB	0.3 GB free	105	llama.cpp	Run
DeepSeek-R1-Distill-Qwen 7B	7.62B	Q6_K	5.8 GB	0.22 GB	6.6 GB	0.4 GB free	47	llama.cpp	Run
Qwen2.5-Coder 7B	7.62B	Q6_K	5.8 GB	0.22 GB	6.6 GB	0.4 GB free	47	llama.cpp	Run
Mistral 7B Instruct v0.3	7.25B	Q6_K	5.5 GB	0.50 GB	6.6 GB	0.4 GB free	49	llama.cpp	Run

Won't fit in VRAM

56 models · some are possible with CPU offload

Model	Params	Quant	Weights	+KV 4K	Total	Over budget	Tok/s	Runtime
Devstral Small 2 24B	24B	Q6_K	18.3 GB	0.63 GB	19.6 GB	+12.6 GB	~2.7	llama.cpp	Why
Mistral Small 3.2 24B	23.6B	Q6_K	18.0 GB	0.63 GB	19.2 GB	+12.2 GB	~2.8	llama.cpp	Why
gpt-oss 20B	20.9B MoE / 3.6B act	MXFP4	10.8 GB	0.10 GB	11.5 GB	+4.5 GB	~15	llama.cpp	Why
Qwen3 14B	14.8B	Q6_K	11.3 GB	0.63 GB	12.5 GB	+5.5 GB	~5.8	llama.cpp	Why
DeepSeek-R1-Distill-Qwen 14B	14.8B	Q6_K	11.3 GB	0.75 GB	12.7 GB	+5.7 GB	~5.7	llama.cpp	Why
Qwen2.5-Coder 14B	14.8B	Q6_K	11.3 GB	0.75 GB	12.7 GB	+5.7 GB	~5.7	llama.cpp	Why
Phi-4 14B	14.7B	Q6_K	11.2 GB	0.78 GB	12.6 GB	+5.6 GB	~5.7	llama.cpp	Why
Ministral 3 14B	13.9B	Q6_K	10.6 GB	0.63 GB	11.8 GB	+4.8 GB	~6.5	llama.cpp	Why
Gemma 3 12B	12.2B	Q6_K	9.3 GB	0.56 GB	10.5 GB	+3.5 GB	~8.5	llama.cpp	Why
Mistral NeMo 12B	12.2B	Q6_K	9.3 GB	0.63 GB	10.5 GB	+3.5 GB	~8.4	llama.cpp	Why
Gemma 4 12B	12B	Q6_K	9.2 GB	0.56 GB	10.3 GB	+3.3 GB	~8.8	llama.cpp	Why
Qwen3.5 9B	9.65B	Q6_K	7.4 GB	0.13 GB	8.1 GB	+1.1 GB	~19	llama.cpp	Why
Ornith 1.5 9B New this week	9.41B	Q6_K	7.2 GB	0.13 GB	7.9 GB	+0.9 GB	~21	llama.cpp	Why
Ministral 3 8B	8.92B	Q6_K	6.8 GB	0.53 GB	7.9 GB	+0.9 GB	~21	llama.cpp	Why
Granite 4.1 8B	8.79B	Q6_K	6.7 GB	0.63 GB	7.9 GB	+0.9 GB	~21	llama.cpp	Why
LFM2.5 8B-A1B	8.47B MoE / 1.5B act	Q6_K	6.5 GB	0.05 GB	7.1 GB	+0.1 GB	~82	llama.cpp	Why
Fara 7B	8.29B	Q6_K	6.3 GB	0.22 GB	7.1 GB	+0.1 GB	~37	llama.cpp	Why
Qwen3 8B	8.19B	Q6_K	6.3 GB	0.56 GB	7.4 GB	+0.4 GB	~30	llama.cpp	Why
Llama 3.1 8B Instruct	8.03B	Q6_K	6.1 GB	0.50 GB	7.2 GB	+0.2 GB	~36	llama.cpp	Why
Olmo 3 7B Instruct	7.3B	Q6_K	5.6 GB	2.00 GB	8.2 GB	+1.2 GB	~21	llama.cpp	Why
Kimi K3 2.8T-A104B New	2780B MoE / 104B act	Q6_K	2123.0 GB	0.11 GB	2123.7 GB	+2116.7 GB	~0.2	llama.cpp	Why
Qwen3.8 2.4T-A95B New	2446B MoE / 95B act	Q6_K	1868.0 GB	0.36 GB	1868.9 GB	+1861.9 GB	~0.2	llama.cpp	Why
DeepSeek V4 Pro 1.6T-A49B New	1650B MoE / 49B act	Q6_K	1260.1 GB	0.27 GB	1260.9 GB	+1253.9 GB	~0.4	llama.cpp	Why
Kimi K2.6 1T-A32B	1027B MoE / 32B act	Q6_K	784.3 GB	0.27 GB	785.2 GB	+778.2 GB	~0.6	llama.cpp	Why
GLM-5.2 744B-A40B	753B MoE / 40B act	Q6_K	575.1 GB	0.34 GB	576.0 GB	+569.0 GB	~0.5	llama.cpp	Why
DeepSeek-R1 671B	671B MoE / 37B act	Q6_K	512.4 GB	0.27 GB	513.3 GB	+506.3 GB	~0.5	llama.cpp	Why
Qwen3.5 397B-A17B	403B MoE / 17B act	Q6_K	307.8 GB	0.12 GB	308.5 GB	+301.5 GB	~1.1	llama.cpp	Why
Ornith 1.5 397B-A17B New this week	397B MoE / 17B act	Q6_K	303.2 GB	0.12 GB	303.9 GB	+296.9 GB	~1.1	llama.cpp	Why
DeepSeek V4 Flash 284B-A13B New	284B MoE / 13B act	Q6_K	216.9 GB	0.19 GB	217.7 GB	+210.7 GB	~1.4	llama.cpp	Why
Qwen3 235B-A22B	235B MoE / 22B act	Q6_K	179.5 GB	0.73 GB	180.8 GB	+173.8 GB	~0.9	llama.cpp	Why
Qwen3.5 122B-A10B	125B MoE / 10B act	Q6_K	95.5 GB	0.09 GB	96.2 GB	+89.2 GB	~1.9	llama.cpp	Why
Nemotron 3 Super 120B-A12B	124B MoE / 12B act	Q6_K	94.7 GB	0.03 GB	95.3 GB	+88.3 GB	~1.6	llama.cpp	Why
Ling 3.0 Flash 124B-A5B New	124B MoE / 5.1B act	Q6_K	94.7 GB	0.03 GB	95.3 GB	+88.3 GB	~3.8	llama.cpp	Why
Mistral Small 4 119B-A6B	119B MoE / 6.5B act	Q6_K	90.9 GB	0.09 GB	91.6 GB	+84.6 GB	~3.0	llama.cpp	Why
gpt-oss 120B	117B MoE / 5.1B act	MXFP4	60.5 GB	0.15 GB	61.3 GB	+54.3 GB	~5.8	llama.cpp	Why
Llama 4 Scout 109B-A17B	109B MoE / 17B act	Q6_K	83.2 GB	0.75 GB	84.6 GB	+77.6 GB	~1.1	llama.cpp	Why
Llama 3.3 70B Instruct	70.6B	Q6_K	53.9 GB	1.25 GB	55.8 GB	+48.8 GB	~0.7	llama.cpp	Why
DeepSeek-R1-Distill-Llama 70B	70.6B	Q6_K	53.9 GB	1.25 GB	55.8 GB	+48.8 GB	~0.7	llama.cpp	Why
Qwen3.6 35B-A3B	35.9B MoE / 3.3B act	Q6_K	27.4 GB	0.08 GB	28.1 GB	+21.1 GB	~6.9	llama.cpp	Why
Ornith 1.5 35B-A3B New this week	35.9B MoE / 3.3B act	Q6_K	27.4 GB	0.08 GB	28.1 GB	+21.1 GB	~6.9	llama.cpp	Why
LLM-jp 4 33B Thinking New this week	33.2B	Q6_K	25.4 GB	1.00 GB	27.0 GB	+20.0 GB	~1.8	llama.cpp	Why
Qwen3 32B	32.8B	Q6_K	25.0 GB	1.00 GB	26.6 GB	+19.6 GB	~1.8	llama.cpp	Why
DeepSeek-R1-Distill-Qwen 32B	32.8B	Q6_K	25.0 GB	1.00 GB	26.6 GB	+19.6 GB	~1.8	llama.cpp	Why
Qwen2.5-Coder 32B	32.8B	Q6_K	25.0 GB	1.00 GB	26.6 GB	+19.6 GB	~1.8	llama.cpp	Why
Olmo 3.1 32B Instruct	32.2B	Q6_K	24.6 GB	1.00 GB	26.2 GB	+19.2 GB	~1.8	llama.cpp	Why
Nemotron 3.5 Lightning 30B-A3B New	31.6B MoE / 3.2B act	Q6_K	24.1 GB	0.02 GB	24.8 GB	+17.8 GB	~7.4	llama.cpp	Why
Gemma 4 31B	31.3B	Q6_K	23.9 GB	1.41 GB	25.9 GB	+18.9 GB	~1.9	llama.cpp	Why
GLM-4.7-Flash 30B-A3B	31.2B MoE / 3B act	Q6_K	23.8 GB	0.21 GB	24.6 GB	+17.6 GB	~7.9	llama.cpp	Why
Qwen3 30B-A3B	30.5B MoE / 3.3B act	Q6_K	23.3 GB	0.38 GB	24.3 GB	+17.3 GB	~7.1	llama.cpp	Why
Qwen3 Coder 30B-A3B	30.5B MoE / 3.3B act	Q6_K	23.3 GB	0.38 GB	24.3 GB	+17.3 GB	~7.1	llama.cpp	Why
Muse Glimmer 30B New	29.8B	Q6_K	22.8 GB	0.13 GB	23.5 GB	+16.5 GB	~2.1	llama.cpp	Why
Granite 4.1 30B	28.9B	Q6_K	22.1 GB	1.00 GB	23.7 GB	+16.7 GB	~2.1	llama.cpp	Why
Qwen3.8 27B New this week	27.8B	Q6_K	21.2 GB	0.25 GB	22.1 GB	+15.1 GB	~2.3	llama.cpp	Why
Qwen3.6 27B	27.8B	Q6_K	21.2 GB	0.25 GB	22.1 GB	+15.1 GB	~2.3	llama.cpp	Why
Gemma 3 27B	27.4B	Q6_K	20.9 GB	0.72 GB	22.2 GB	+15.2 GB	~2.3	llama.cpp	Why
Gemma 4 26B-A4B	26.5B MoE / 3.8B act	Q6_K	20.2 GB	0.35 GB	21.2 GB	+14.2 GB	~6.5	llama.cpp	Why

Totals = quantised weights + f16 KV cache at 4K tokens + 0.6 GB runtime overhead, against 7.0 GB usable VRAM (8 GB less display and driver reserve). Tokens per second are estimated from 448 GB/s peak memory bandwidth at batch 1 — not measured. Read the method.