What LLMs can a GeForce RTX 3090 Ti run?

Your rig

GeForce RTX 3090 Ti · 24 GB

8 GB system RAM · Ampere · 1008 GB/s · 22.4 GB usable VRAM

Which one should I actually run?

Best models for your GeForce RTX 3090 Ti

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 128K. 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	Gemma 4 12B Google · Apache 2.0	The 12 GB generalist: text, image and audio in, 140+ languages.	Q4_K_M · 15.7 GB	90	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 · 10.0 GB	112	Runs great Run
Best reasoning	gpt-oss 20B OpenAI · Apache 2.0	Low/medium/high reasoning effort in 13 GB.	MXFP4 · 14.4 GB	126	Runs great Run
Best for writing	Gemma 4 12B Google · Apache 2.0	The 12 GB writing pick; 140+ languages.	Q4_K_M · 15.7 GB	90	Runs great Run
Best vision	Gemma 4 26B-A4B Google · Apache 2.0	Vision at MoE speed in 18 GB.	Q4_K_M · 20.7 GB	110	Tight fit Run
Best for agents	Muse Glimmer 30B New Meta · Apache 2.0	Distilled specifically for always-on local agent workflows.	Q4_K_M · 19.1 GB	36	Tight fit Run
Best translation	Gemma 4 12B Google · Apache 2.0	Broad language coverage on a 12 GB card.	Q4_K_M · 15.7 GB	90	Runs great Run
Fastest good model	Gemma 4 26B-A4B Google · Apache 2.0	3.8B active and a small file — the quickest Gemma 4 with vision.	Q4_K_M · 20.7 GB	110	Tight fit Run
Best long context	Nemotron 3.5 Lightning 30B-A3B New NVIDIA · OpenMDW-1.1	262K, and a Mamba hybrid whose cache barely grows.	Q4_K_M · 19.1 GB at 128K context	130	Tight fit Run

Everything that fits

Runs great

29 of 76 · fits with headroom for a longer prompt

Model	Params	Quant	Weights	+KV 128K	Total	VRAM headroom	Tok/s	Runtime
gpt-oss 20B	20.9B MoE / 3.6B act	MXFP4	10.8 GB	3.00 GB	14.4 GB	8.0 GB free	126	Ollama	Run
Phi-4 14B	14.7B	Q4_K_M	8.3 GB	3.13 GB	12.0 GB	10.4 GB free	74	Ollama	Run
Gemma 3 12B	12.2B	Q4_K_M	6.9 GB	8.31 GB	15.8 GB	6.6 GB free	89	Ollama	Run
Gemma 4 12B	12B	Q4_K_M	6.7 GB	8.31 GB	15.7 GB	6.7 GB free	90	Ollama	Run
Qwen3.5 9B	9.65B	Q4_K_M	5.4 GB	4.00 GB	10.0 GB	12.4 GB free	112	Ollama	Run
Ornith 1.5 9B New this week	9.41B	Q4_K_M	5.3 GB	4.00 GB	9.9 GB	12.5 GB free	115	Ollama	Run
LFM2.5 8B-A1B	8.47B MoE / 1.5B act	Q4_K_M	4.8 GB	1.46 GB	6.8 GB	15.6 GB free	278	Ollama	Run
Fara 7B	8.29B	Q4_K_M	4.7 GB	6.84 GB	12.1 GB	10.3 GB free	131	llama.cpp	Run
Gemma 4 E4B	8.0B	Q4_K_M	4.5 GB	1.78 GB	6.9 GB	15.5 GB free	136	Ollama	Run
Ling 3.0 Tiny 7.9B-A1.3B New	7.9B MoE / 1.3B act	Q4_K_M	4.4 GB	0.84 GB	5.9 GB	16.5 GB free	321	llama.cpp	Run
DeepSeek-R1-Distill-Qwen 7B	7.62B	Q4_K_M	4.3 GB	7.00 GB	11.9 GB	10.5 GB free	142	Ollama	Run
Qwen2.5-Coder 7B	7.62B	Q4_K_M	4.3 GB	7.00 GB	11.9 GB	10.5 GB free	142	Ollama	Run
Olmo 3 7B Instruct	7.3B	Q4_K_M	4.1 GB	9.50 GB	14.2 GB	8.2 GB free	149	Ollama	Run
Mistral 7B Instruct v0.3	7.25B	Q4_K_M	4.1 GB	4.00 GB	8.7 GB	13.7 GB free	150	Ollama	Run
Gemma 4 E2B	5.1B	Q4_K_M	2.9 GB	0.89 GB	4.4 GB	18.0 GB free	213	Ollama	Run
Qwen3.5 4B	4.66B	Q4_K_M	2.6 GB	4.00 GB	7.2 GB	15.2 GB free	233	Ollama	Run
Gemma 3 4B	4.3B	Q4_K_M	2.4 GB	3.11 GB	6.1 GB	16.3 GB free	252	Ollama	Run
Qwen3 4B	4.02B	Q4_K_M	2.3 GB	4.50 GB	7.4 GB	15.0 GB free	270	Ollama	Run
Ministral 3 3B	3.85B	Q4_K_M	2.2 GB	13.00 GB	15.8 GB	6.6 GB free	282	Ollama	Run
Phi-4-mini 3.8B	3.84B	Q4_K_M	2.2 GB	16.00 GB	18.8 GB	3.6 GB free	283	Ollama	Run
Granite 4.1 3B	3.4B	Q4_K_M	1.9 GB	10.00 GB	12.5 GB	9.9 GB free	319	Ollama	Run
Llama 3.2 3B Instruct	3.21B	Q4_K_M	1.8 GB	14.00 GB	16.4 GB	6.0 GB free	338	Ollama	Run
LFM2.5 2.6B New	2.7B	Q4_K_M	1.5 GB	2.00 GB	4.1 GB	18.3 GB free	402	llama.cpp	Run
Qwen3.5 2B	2.27B	Q4_K_M	1.3 GB	1.50 GB	3.4 GB	19.0 GB free	478	Ollama	Run
Qwen3 1.7B	1.72B	Q4_K_M	1.0 GB	3.50 GB	5.1 GB	17.3 GB free	631	Ollama	Run
Llama 3.2 1B Instruct	1.24B	Q4_K_M	0.7 GB	4.00 GB	5.3 GB	17.1 GB free	875	Ollama	Run
Gemma 3 1B	1.0B	Q4_K_M	0.6 GB	0.14 GB	1.3 GB	21.1 GB free	1085	Ollama	Run
Qwen3.5 0.8B	0.87B	Q4_K_M	0.5 GB	1.50 GB	2.6 GB	19.8 GB free	1247	Ollama	Run
Qwen3 0.6B	0.6B	Q4_K_M	0.3 GB	3.50 GB	4.4 GB	18.0 GB free	1809	Ollama	Run

Runs — tight

4 models · fits at 128K, drop context or quant to go longer

Model	Params	Quant	Weights	+KV 128K	Total	VRAM headroom	Tok/s	Runtime
Nemotron 3.5 Lightning 30B-A3B New	31.6B MoE / 3.2B act	Q4_K_M	17.8 GB	0.75 GB	19.1 GB	3.3 GB free	130	llama.cpp	Run
Muse Glimmer 30B New	29.8B	Q4_K_M	16.8 GB	1.70 GB	19.1 GB	3.3 GB free	36	llama.cpp	Run
Gemma 4 26B-A4B	26.5B MoE / 3.8B act	Q4_K_M	14.9 GB	5.20 GB	20.7 GB	1.7 GB free	110	llama.cpp	Run
Llama 3.1 8B Instruct	8.03B	Q4_K_M	4.5 GB	16.00 GB	21.1 GB	1.3 GB free	135	llama.cpp	Run

Won't fit in VRAM

43 models · some are possible with CPU offload

Model	Params	Quant	Weights	+KV 128K	Total	Over budget	Tok/s	Runtime
Qwen3.6 35B-A3B	35.9B MoE / 3.3B act	Q4_K_M	20.2 GB	2.50 GB	23.3 GB	+0.9 GB	~75	llama.cpp	Why
Ornith 1.5 35B-A3B New this week	35.9B MoE / 3.3B act	Q4_K_M	20.2 GB	2.50 GB	23.3 GB	+0.9 GB	~75	llama.cpp	Why
Olmo 3.1 32B Instruct	32.2B	Q4_K_M	18.1 GB	4.75 GB	23.5 GB	+1.1 GB	~18	llama.cpp	Why
GLM-4.7-Flash 30B-A3B	31.2B MoE / 3B act	Q4_K_M	17.5 GB	6.61 GB	24.8 GB	+2.4 GB	~45	llama.cpp	Why
Qwen3.8 27B New this week	27.8B	Q4_K_M	15.6 GB	8.00 GB	24.2 GB	+1.8 GB	~14	llama.cpp	Why
Qwen3.6 27B	27.8B	Q4_K_M	15.6 GB	8.00 GB	24.2 GB	+1.8 GB	~14	llama.cpp	Why
Gemma 3 27B	27.4B	Q4_K_M	15.4 GB	10.41 GB	26.4 GB	+4.0 GB	~7.7	llama.cpp	Why
Qwen3 14B	14.8B	Q4_K_M	8.3 GB	20.00 GB	28.9 GB	+6.5 GB	~5.5	llama.cpp	Why
Ministral 3 14B	13.9B	Q4_K_M	7.8 GB	20.00 GB	28.4 GB	+6.0 GB	~5.9	llama.cpp	Why
Mistral NeMo 12B	12.2B	Q4_K_M	6.9 GB	20.00 GB	27.5 GB	+5.1 GB	~7.0	llama.cpp	Why
Ministral 3 8B	8.92B	Q4_K_M	5.0 GB	17.00 GB	22.6 GB	+0.2 GB	~72	llama.cpp	Why
Granite 4.1 8B	8.79B	Q4_K_M	4.9 GB	20.00 GB	25.5 GB	+3.1 GB	~11	llama.cpp	Why
Qwen3 8B	8.19B	Q4_K_M	4.6 GB	18.00 GB	23.2 GB	+0.8 GB	~35	llama.cpp	Why
Kimi K3 2.8T-A104B New	2780B MoE / 104B act	Q4_K_M	1563.2 GB	3.38 GB	1567.1 GB	+1544.7 GB	~0.2	llama.cpp	Why
Qwen3.8 2.4T-A95B New	2446B MoE / 95B act	Q4_K_M	1375.4 GB	11.50 GB	1387.5 GB	+1365.1 GB	~0.3	llama.cpp	Why
DeepSeek V4 Pro 1.6T-A49B New	1650B MoE / 49B act	Q4_K_M	927.8 GB	8.58 GB	937.0 GB	+914.6 GB	~0.5	llama.cpp	Why
Kimi K2.6 1T-A32B	1027B MoE / 32B act	Q4_K_M	577.5 GB	8.58 GB	586.6 GB	+564.2 GB	~0.8	llama.cpp	Why
GLM-5.2 744B-A40B	753B MoE / 40B act	Q4_K_M	423.4 GB	10.97 GB	435.0 GB	+412.6 GB	~0.6	llama.cpp	Why
DeepSeek-R1 671B	671B MoE / 37B act	Q4_K_M	377.3 GB	8.58 GB	386.5 GB	+364.1 GB	~0.7	llama.cpp	Why
Qwen3.5 397B-A17B	403B MoE / 17B act	Q4_K_M	226.6 GB	3.75 GB	231.0 GB	+208.6 GB	~1.6	llama.cpp	Why
Ornith 1.5 397B-A17B New this week	397B MoE / 17B act	Q4_K_M	223.2 GB	3.75 GB	227.6 GB	+205.2 GB	~1.6	llama.cpp	Why
DeepSeek V4 Flash 284B-A13B New	284B MoE / 13B act	Q4_K_M	159.7 GB	6.05 GB	166.3 GB	+143.9 GB	~2.1	llama.cpp	Why
Qwen3 235B-A22B	235B MoE / 22B act	Q4_K_M	132.1 GB	23.50 GB	156.2 GB	+133.8 GB	~1.1	llama.cpp	Why
Qwen3.5 122B-A10B	125B MoE / 10B act	Q4_K_M	70.3 GB	3.00 GB	73.9 GB	+51.5 GB	~3.3	llama.cpp	Why
Nemotron 3 Super 120B-A12B	124B MoE / 12B act	Q4_K_M	69.7 GB	1.00 GB	71.3 GB	+48.9 GB	~2.9	llama.cpp	Why
Ling 3.0 Flash 124B-A5B New	124B MoE / 5.1B act	Q4_K_M	69.7 GB	0.98 GB	71.3 GB	+48.9 GB	~6.8	llama.cpp	Why
Mistral Small 4 119B-A6B	119B MoE / 6.5B act	Q4_K_M	66.9 GB	2.81 GB	70.3 GB	+47.9 GB	~5.2	llama.cpp	Why
gpt-oss 120B	117B MoE / 5.1B act	MXFP4	60.5 GB	4.50 GB	65.6 GB	+43.2 GB	~7.2	llama.cpp	Why
Llama 4 Scout 109B-A17B	109B MoE / 17B act	Q4_K_M	61.3 GB	7.13 GB	69.0 GB	+46.6 GB	~1.9	llama.cpp	Why
Llama 3.3 70B Instruct	70.6B	Q4_K_M	39.7 GB	40.00 GB	80.3 GB	+57.9 GB	~0.9	llama.cpp	Why
DeepSeek-R1-Distill-Llama 70B	70.6B	Q4_K_M	39.7 GB	40.00 GB	80.3 GB	+57.9 GB	~0.9	llama.cpp	Why
LLM-jp 4 33B Thinking New this week	33.2B	Q4_K_M	18.7 GB	16.00 GB	35.3 GB	+12.9 GB	~2.7	llama.cpp	Why
Qwen3 32B	32.8B	Q4_K_M	18.4 GB	32.00 GB	51.0 GB	+28.6 GB	~2.0	llama.cpp	Why
DeepSeek-R1-Distill-Qwen 32B	32.8B	Q4_K_M	18.4 GB	32.00 GB	51.0 GB	+28.6 GB	~2.0	llama.cpp	Why
Qwen2.5-Coder 32B	32.8B	Q4_K_M	18.4 GB	32.00 GB	51.0 GB	+28.6 GB	~2.0	llama.cpp	Why
Gemma 4 31B	31.3B	Q4_K_M	17.6 GB	20.78 GB	39.0 GB	+16.6 GB	~2.2	llama.cpp	Why
Qwen3 30B-A3B	30.5B MoE / 3.3B act	Q4_K_M	17.1 GB	12.00 GB	29.7 GB	+7.3 GB	~16	llama.cpp	Why
Qwen3 Coder 30B-A3B	30.5B MoE / 3.3B act	Q4_K_M	17.1 GB	12.00 GB	29.7 GB	+7.3 GB	~16	llama.cpp	Why
Granite 4.1 30B	28.9B	Q4_K_M	16.3 GB	32.00 GB	48.9 GB	+26.5 GB	~2.2	llama.cpp	Why
Devstral Small 2 24B	24B	Q4_K_M	13.5 GB	20.00 GB	34.1 GB	+11.7 GB	~3.1	llama.cpp	Why
Mistral Small 3.2 24B	23.6B	Q4_K_M	13.3 GB	20.00 GB	33.9 GB	+11.5 GB	~3.1	llama.cpp	Why
DeepSeek-R1-Distill-Qwen 14B	14.8B	Q4_K_M	8.3 GB	24.00 GB	32.9 GB	+10.5 GB	~4.4	llama.cpp	Why
Qwen2.5-Coder 14B	14.8B	Q4_K_M	8.3 GB	24.00 GB	32.9 GB	+10.5 GB	~4.4	llama.cpp	Why

Totals = quantised weights + f16 KV cache at 128K tokens + 0.6 GB runtime overhead, against 22.4 GB usable VRAM (24 GB less display and driver reserve). Tokens per second are estimated from 1008 GB/s peak memory bandwidth at batch 1 — not measured. Read the method.