What LLMs can a GeForce RTX 3080 12 GB run?

Your rig

GeForce RTX 3080 12 GB · 12 GB

16 GB system RAM · Ampere · 912 GB/s · 10.6 GB usable VRAM

Which one should I actually run?

Best models for your GeForce RTX 3080 12 GB

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 Q4_K_M and 32K. 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 9B Alibaba · Apache 2.0	The 8–12 GB default of 2026 — beats every older 8B, with vision.	Q4_K_M · 7.0 GB	102	Runs great Run
Best for coding	Qwen3.5 9B Alibaba · Apache 2.0	The best coding model for 8–12 GB cards.	Q4_K_M · 7.0 GB	102	Runs great Run
Best reasoning	Qwen3.5 9B Alibaba · Apache 2.0	Thinking mode on a 12 GB card — ahead of the 2025 R1 distills.	Q4_K_M · 7.0 GB	102	Runs great Run
Best for writing	Gemma 4 12B Google · Apache 2.0	The 12 GB writing pick; 140+ languages.	Q4_K_M · 9.7 GB	82	Tight fit Run
Best vision	Qwen3.5 9B Alibaba · Apache 2.0	Vision on an 8–12 GB card.	Q4_K_M · 7.0 GB	102	Runs great Run
Best for agents	Fara 7B Microsoft · MIT	Web computer-use only — clicks and fills forms from screenshots, and stops to ask before anything irreversible.	Q4_K_M · 7.0 GB	118	Runs great Run
Best translation	Qwen3.5 9B Alibaba · Apache 2.0	Strong CJK and European translation in 8–12 GB.	Q4_K_M · 7.0 GB	102	Runs great Run
Fastest good model	LFM2.5 8B-A1B Liquid AI · LFM Open License v1.0	1.5B active; designed for laptops without a GPU.	Q4_K_M · 5.7 GB	252	Runs great Run
Best long context	Qwen3.5 4B Alibaba · Apache 2.0	262K on 8 GB.	Q4_K_M · 7.2 GB at 128K context	211	Runs great Run

Everything that fits

Runs great

24 of 76 · fits with headroom for a longer prompt

Model	Params	Quant	Weights	+KV 32K	Total	VRAM headroom	Tok/s	Runtime
Qwen3.5 9B	9.65B	Q4_K_M	5.4 GB	1.00 GB	7.0 GB	3.6 GB free	102	Ollama	Run
Ornith 1.5 9B New this week	9.41B	Q4_K_M	5.3 GB	1.00 GB	6.9 GB	3.7 GB free	104	Ollama	Run
LFM2.5 8B-A1B	8.47B MoE / 1.5B act	Q4_K_M	4.8 GB	0.38 GB	5.7 GB	4.9 GB free	252	Ollama	Run
Fara 7B	8.29B	Q4_K_M	4.7 GB	1.75 GB	7.0 GB	3.6 GB free	118	llama.cpp	Run
Gemma 4 E4B	8.0B	Q4_K_M	4.5 GB	0.47 GB	5.6 GB	5.0 GB free	123	Ollama	Run
Ling 3.0 Tiny 7.9B-A1.3B New	7.9B MoE / 1.3B act	Q4_K_M	4.4 GB	0.21 GB	5.3 GB	5.3 GB free	290	llama.cpp	Run
DeepSeek-R1-Distill-Qwen 7B	7.62B	Q4_K_M	4.3 GB	1.75 GB	6.6 GB	4.0 GB free	129	Ollama	Run
Qwen2.5-Coder 7B	7.62B	Q4_K_M	4.3 GB	1.75 GB	6.6 GB	4.0 GB free	129	Ollama	Run
Mistral 7B Instruct v0.3	7.25B	Q4_K_M	4.1 GB	4.00 GB	8.7 GB	1.9 GB free	135	Ollama	Run
Gemma 4 E2B	5.1B	Q4_K_M	2.9 GB	0.23 GB	3.7 GB	6.9 GB free	193	Ollama	Run
Qwen3.5 4B	4.66B	Q4_K_M	2.6 GB	1.00 GB	4.2 GB	6.4 GB free	211	Ollama	Run
Gemma 3 4B	4.3B	Q4_K_M	2.4 GB	0.86 GB	3.9 GB	6.7 GB free	228	Ollama	Run
Qwen3 4B	4.02B	Q4_K_M	2.3 GB	4.50 GB	7.4 GB	3.2 GB free	244	Ollama	Run
Ministral 3 3B	3.85B	Q4_K_M	2.2 GB	3.25 GB	6.0 GB	4.6 GB free	255	Ollama	Run
Phi-4-mini 3.8B	3.84B	Q4_K_M	2.2 GB	4.00 GB	6.8 GB	3.8 GB free	256	Ollama	Run
Granite 4.1 3B	3.4B	Q4_K_M	1.9 GB	2.50 GB	5.0 GB	5.6 GB free	289	Ollama	Run
Llama 3.2 3B Instruct	3.21B	Q4_K_M	1.8 GB	3.50 GB	5.9 GB	4.7 GB free	306	Ollama	Run
LFM2.5 2.6B New	2.7B	Q4_K_M	1.5 GB	0.50 GB	2.6 GB	8.0 GB free	364	llama.cpp	Run
Qwen3.5 2B	2.27B	Q4_K_M	1.3 GB	0.38 GB	2.3 GB	8.3 GB free	433	Ollama	Run
Qwen3 1.7B	1.72B	Q4_K_M	1.0 GB	3.50 GB	5.1 GB	5.5 GB free	571	Ollama	Run
Llama 3.2 1B Instruct	1.24B	Q4_K_M	0.7 GB	1.00 GB	2.3 GB	8.3 GB free	792	Ollama	Run
Gemma 3 1B	1.0B	Q4_K_M	0.6 GB	0.14 GB	1.3 GB	9.3 GB free	982	Ollama	Run
Qwen3.5 0.8B	0.87B	Q4_K_M	0.5 GB	0.38 GB	1.5 GB	9.1 GB free	1129	Ollama	Run
Qwen3 0.6B	0.6B	Q4_K_M	0.3 GB	3.50 GB	4.4 GB	6.2 GB free	1636	Ollama	Run

Runs — tight

7 models · fits at 32K, drop context or quant to go longer

Model	Params	Quant	Weights	+KV 32K	Total	VRAM headroom	Tok/s	Runtime
Gemma 3 12B	12.2B	Q4_K_M	6.9 GB	2.31 GB	9.8 GB	0.8 GB free	80	llama.cpp	Run
Gemma 4 12B	12B	Q4_K_M	6.7 GB	2.31 GB	9.7 GB	0.9 GB free	82	llama.cpp	Run
Ministral 3 8B	8.92B	Q4_K_M	5.0 GB	4.25 GB	9.9 GB	0.7 GB free	110	llama.cpp	Run
Granite 4.1 8B	8.79B	Q4_K_M	4.9 GB	5.00 GB	10.5 GB	0.1 GB free	112	llama.cpp	Run
Qwen3 8B	8.19B	Q4_K_M	4.6 GB	4.50 GB	9.7 GB	0.9 GB free	120	llama.cpp	Run
Llama 3.1 8B Instruct	8.03B	Q4_K_M	4.5 GB	4.00 GB	9.1 GB	1.5 GB free	122	llama.cpp	Run
Olmo 3 7B Instruct	7.3B	Q4_K_M	4.1 GB	5.50 GB	10.2 GB	0.4 GB free	135	llama.cpp	Run

Won't fit in VRAM

45 models · some are possible with CPU offload

Model	Params	Quant	Weights	+KV 32K	Total	Over budget	Tok/s	Runtime
Qwen3.6 35B-A3B	35.9B MoE / 3.3B act	Q4_K_M	20.2 GB	0.63 GB	21.4 GB	+10.8 GB	~13	llama.cpp	Why
Ornith 1.5 35B-A3B New this week	35.9B MoE / 3.3B act	Q4_K_M	20.2 GB	0.63 GB	21.4 GB	+10.8 GB	~13	llama.cpp	Why
Olmo 3.1 32B Instruct	32.2B	Q4_K_M	18.1 GB	2.75 GB	21.5 GB	+10.9 GB	~3.2	llama.cpp	Why
Nemotron 3.5 Lightning 30B-A3B New	31.6B MoE / 3.2B act	Q4_K_M	17.8 GB	0.19 GB	18.6 GB	+8.0 GB	~16	llama.cpp	Why
Gemma 4 31B	31.3B	Q4_K_M	17.6 GB	5.78 GB	24.0 GB	+13.4 GB	~2.7	llama.cpp	Why
GLM-4.7-Flash 30B-A3B	31.2B MoE / 3B act	Q4_K_M	17.5 GB	1.65 GB	19.8 GB	+9.2 GB	~15	llama.cpp	Why
Qwen3 30B-A3B	30.5B MoE / 3.3B act	Q4_K_M	17.1 GB	3.00 GB	20.7 GB	+10.1 GB	~12	llama.cpp	Why
Qwen3 Coder 30B-A3B	30.5B MoE / 3.3B act	Q4_K_M	17.1 GB	3.00 GB	20.7 GB	+10.1 GB	~12	llama.cpp	Why
Muse Glimmer 30B New	29.8B	Q4_K_M	16.8 GB	0.48 GB	17.8 GB	+7.2 GB	~4.6	llama.cpp	Why
Qwen3.8 27B New this week	27.8B	Q4_K_M	15.6 GB	2.00 GB	18.2 GB	+7.6 GB	~4.5	llama.cpp	Why
Qwen3.6 27B	27.8B	Q4_K_M	15.6 GB	2.00 GB	18.2 GB	+7.6 GB	~4.5	llama.cpp	Why
Gemma 3 27B	27.4B	Q4_K_M	15.4 GB	2.91 GB	18.9 GB	+8.3 GB	~4.1	llama.cpp	Why
Gemma 4 26B-A4B	26.5B MoE / 3.8B act	Q4_K_M	14.9 GB	1.45 GB	16.9 GB	+6.3 GB	~14	llama.cpp	Why
Devstral Small 2 24B	24B	Q4_K_M	13.5 GB	5.00 GB	19.1 GB	+8.5 GB	~4.1	llama.cpp	Why
Mistral Small 3.2 24B	23.6B	Q4_K_M	13.3 GB	5.00 GB	18.9 GB	+8.3 GB	~4.2	llama.cpp	Why
gpt-oss 20B	20.9B MoE / 3.6B act	MXFP4	10.8 GB	0.75 GB	12.2 GB	+1.6 GB	~37	llama.cpp	Why
Qwen3 14B	14.8B	Q4_K_M	8.3 GB	5.00 GB	13.9 GB	+3.3 GB	~9.9	llama.cpp	Why
DeepSeek-R1-Distill-Qwen 14B	14.8B	Q4_K_M	8.3 GB	6.00 GB	14.9 GB	+4.3 GB	~7.9	llama.cpp	Why
Qwen2.5-Coder 14B	14.8B	Q4_K_M	8.3 GB	6.00 GB	14.9 GB	+4.3 GB	~7.9	llama.cpp	Why
Phi-4 14B	14.7B	Q4_K_M	8.3 GB	3.13 GB	12.0 GB	+1.4 GB	~20	llama.cpp	Why
Ministral 3 14B	13.9B	Q4_K_M	7.8 GB	5.00 GB	13.4 GB	+2.8 GB	~12	llama.cpp	Why
Mistral NeMo 12B	12.2B	Q4_K_M	6.9 GB	5.00 GB	12.5 GB	+1.9 GB	~17	llama.cpp	Why
Kimi K3 2.8T-A104B New	2780B MoE / 104B act	Q4_K_M	1563.2 GB	0.84 GB	1564.6 GB	+1554.0 GB	~0.2	llama.cpp	Why
Qwen3.8 2.4T-A95B New	2446B MoE / 95B act	Q4_K_M	1375.4 GB	2.88 GB	1378.8 GB	+1368.2 GB	~0.3	llama.cpp	Why
DeepSeek V4 Pro 1.6T-A49B New	1650B MoE / 49B act	Q4_K_M	927.8 GB	2.14 GB	930.5 GB	+919.9 GB	~0.5	llama.cpp	Why
Kimi K2.6 1T-A32B	1027B MoE / 32B act	Q4_K_M	577.5 GB	2.14 GB	580.2 GB	+569.6 GB	~0.8	llama.cpp	Why
GLM-5.2 744B-A40B	753B MoE / 40B act	Q4_K_M	423.4 GB	2.74 GB	426.7 GB	+416.1 GB	~0.6	llama.cpp	Why
DeepSeek-R1 671B	671B MoE / 37B act	Q4_K_M	377.3 GB	2.14 GB	380.0 GB	+369.4 GB	~0.7	llama.cpp	Why
Qwen3.5 397B-A17B	403B MoE / 17B act	Q4_K_M	226.6 GB	0.94 GB	228.1 GB	+217.5 GB	~1.5	llama.cpp	Why
Ornith 1.5 397B-A17B New this week	397B MoE / 17B act	Q4_K_M	223.2 GB	0.94 GB	224.8 GB	+214.2 GB	~1.5	llama.cpp	Why
DeepSeek V4 Flash 284B-A13B New	284B MoE / 13B act	Q4_K_M	159.7 GB	1.51 GB	161.8 GB	+151.2 GB	~2.0	llama.cpp	Why
Qwen3 235B-A22B	235B MoE / 22B act	Q4_K_M	132.1 GB	5.88 GB	138.6 GB	+128.0 GB	~1.2	llama.cpp	Why
Qwen3.5 122B-A10B	125B MoE / 10B act	Q4_K_M	70.3 GB	0.75 GB	71.6 GB	+61.0 GB	~2.8	llama.cpp	Why
Nemotron 3 Super 120B-A12B	124B MoE / 12B act	Q4_K_M	69.7 GB	0.25 GB	70.6 GB	+60.0 GB	~2.4	llama.cpp	Why
Ling 3.0 Flash 124B-A5B New	124B MoE / 5.1B act	Q4_K_M	69.7 GB	0.25 GB	70.6 GB	+60.0 GB	~5.6	llama.cpp	Why
Mistral Small 4 119B-A6B	119B MoE / 6.5B act	Q4_K_M	66.9 GB	0.70 GB	68.2 GB	+57.6 GB	~4.4	llama.cpp	Why
gpt-oss 120B	117B MoE / 5.1B act	MXFP4	60.5 GB	1.13 GB	62.2 GB	+51.6 GB	~6.1	llama.cpp	Why
Llama 4 Scout 109B-A17B	109B MoE / 17B act	Q4_K_M	61.3 GB	2.63 GB	64.5 GB	+53.9 GB	~1.6	llama.cpp	Why
Llama 3.3 70B Instruct	70.6B	Q4_K_M	39.7 GB	10.00 GB	50.3 GB	+39.7 GB	~0.9	llama.cpp	Why
DeepSeek-R1-Distill-Llama 70B	70.6B	Q4_K_M	39.7 GB	10.00 GB	50.3 GB	+39.7 GB	~0.9	llama.cpp	Why
LLM-jp 4 33B Thinking New this week	33.2B	Q4_K_M	18.7 GB	8.00 GB	27.3 GB	+16.7 GB	~2.2	llama.cpp	Why
Qwen3 32B	32.8B	Q4_K_M	18.4 GB	8.00 GB	27.0 GB	+16.4 GB	~2.2	llama.cpp	Why
DeepSeek-R1-Distill-Qwen 32B	32.8B	Q4_K_M	18.4 GB	8.00 GB	27.0 GB	+16.4 GB	~2.2	llama.cpp	Why
Qwen2.5-Coder 32B	32.8B	Q4_K_M	18.4 GB	8.00 GB	27.0 GB	+16.4 GB	~2.2	llama.cpp	Why
Granite 4.1 30B	28.9B	Q4_K_M	16.3 GB	8.00 GB	24.9 GB	+14.3 GB	~2.5	llama.cpp	Why

Totals = quantised weights + f16 KV cache at 32K tokens + 0.6 GB runtime overhead, against 10.6 GB usable VRAM (12 GB less display and driver reserve). Tokens per second are estimated from 912 GB/s peak memory bandwidth at batch 1 — not measured. Read the method.