RunsOnMy ModelsGPUs & MacsAPI pricesVRAM calculatorNew

What AI models run on the 2x RTX 3090?

The 2x RTX 3090 has 2× 24 GB of VRAM (936 GB/s). About 45.6 GB is usable for a model. 214 of 285 open models we track fit at 8K context.

214models fit (8K ctx)
212still fit at 32K ctx
127Blargest that fits
936 GB/smemory bandwidth

Models that fit, largest first

ModelParamsBest quant (8K)Needs32K contextMax tok/s (est.)
Ling 3.0 flash127B (5.6B act.)Q2_K43.8 GBQ2_K464details
Ornith 1.5 122B125B (13B act.)Q2_K44.7 GBQ2_K196details
GLM 4.5 Air110B (15B act.)Q2_K44.3 GBno152details
Llama 4 Scout 17B 16E Instruct109B (18B act.)Q2_K39.1 GBQ2_K142details
Llama 4 Scout 17B 16E109B (18B act.)Q2_K40.2 GBQ2_K138details
GLM 4.5V108B (14B act.)Q2_K39.7 GBQ2_K175details
GLM 4.6V108B (14B act.)Q2_K43.0 GBno161details
Hunyuan A13B Instruct80B (13B act.)Q3_K_M37.6 GBQ3_K_M150details
Kimi Dev 72B73BQ3_K_M38.3 GBQ2_K25details
Llama 3.3 70B Instruct71BQ3_K_M35.3 GBQ2_K27details
DeepSeek R1 Distill Llama 70B71BQ3_K_M35.3 GBQ2_K27details
Llama 3.1 70B71BQ3_K_M35.1 GBQ2_K27details
Kimi Linear 48B A3B Instruct49B (3.0B act.)Q6_K38.6 GBQ6_K379details
Nous Hermes 2 Mixtral 8x7B DPO47B (13B act.)Q6_K37.2 GBQ6_K88details
falcon 40b42BQ6_K33.6 GBQ6_K27details
flint40B (1.3B act.)Q8_040.3 GBQ8_0704details
Maxwell V1 Flash37B (2.3B act.)Q8_037.6 GBQ8_0388details
Hermes 4.3 36B36BQ8_038.5 GBQ6_K24details
Seed OSS 36B Instruct36BQ8_038.5 GBQ6_K24details
Qwen3.6 35B A3B36B (3.0B act.)Q8_036.2 GBQ8_0297details
Ornith 1.5 35B A3B36B (3.0B act.)Q8_036.2 GBQ8_0297details
Qwen3.5 35B A3B36B (3.0B act.)Q8_035.4 GBQ8_0304details
Axion 1.0 35B35B (3.9B act.)Q8_035.8 GBQ8_0226details
Qwen AgentWorld 35B A3B35B (3.0B act.)Q8_035.4 GBQ8_0293details
Yi 34B 200K34BQ8_036.4 GBQ6_K26details
Yi 34B34BQ8_036.4 GBQ6_K26details
Yi 34B Chat34BQ8_036.4 GBQ6_K26details
Yi 1.5 34B Chat34BQ8_036.4 GBQ6_K26details
Nous Hermes 2 Yi 34B34BQ8_036.4 GBQ6_K26details
DeepSeek R1 Distill Qwen 32B33BQ8_035.1 GBQ6_K27details
Qwen3 32B33BQ8_035.1 GBQ6_K27details
GLM Z1 32B 041433BQ8_033.4 GBQ8_027details
GLM 4 32B 041433BQ8_033.4 GBQ8_027details
granite 4.0 h small32B (8.8B act.)Q8_032.6 GBQ8_0100details
gemma 4 31B it31BQ8_033.3 GBQ8_029details
GLM 4.7 Flash31B (4.6B act.)Q8_030.8 GBQ8_0199details
Qwen3 Coder 30B A3B Instruct31B (3.0B act.)Q8_031.7 GBQ8_0293details
North Mini Code 1.030B (3.3B act.)Q8_031.6 GBQ8_0266details
Hy Memory 30B A3B30B (3.0B act.)Q8_031.1 GBQ8_0294details
Muse Glimmer 30B30BQ8_028.5 GBQ8_032details
granite 4.2 30b29BQ8_031.6 GBQ8_030details
Qwen3.8 27B28BQ8_028.4 GBQ8_032details
Qwen3.6 27B28BQ8_028.0 GBQ8_033details
Qwen3.5 27B28BQ8_028.0 GBQ8_033details
gemma 3 27b it27BQ8_028.7 GBQ8_033details
Arete 27B27BQ8_028.1 GBQ8_033details
MiniMax H3 Image PE27BQ8_028.0 GBQ8_033details
Trinity Mini26B (2.0B act.)Q8_026.9 GBQ8_0448details
GLiDE 27B26BQ8_027.2 GBQ8_034details
diffusiongemma 26B A4B it26B (4.0B act.)Q8_026.4 GBQ8_0225details
gemma 4 26B A4B it26B (4.0B act.)Q8_026.4 GBQ8_0225details
LFM2.5 24B A2B24B (2.0B act.)Q8_024.5 GBQ8_0440details
ERNIE 4.5 21B A3B PT22BQ8_022.6 GBQ8_040details
ERNIE 4.5 21B A3B Thinking22BQ8_022.6 GBQ8_040details
gpt oss safeguard 20b22B (4.8B act.)F1613.8 GBF16305details
gpt oss 20b21B (4.2B act.)F1613.8 GBF16338details
Groot 19B A3B 26102319B (3.0B act.)F1636.4 GBF16160details
Kimi VL A3B Thinking 250616B (3.0B act.)Q8_016.8 GBQ8_0302details
Kimi VL A3B Instruct16B (3.0B act.)F1631.5 GBF16156details
Kimi VL A3B Thinking16B (3.0B act.)F1631.5 GBF16156details
deepseek moe 16b base16B (2.8B act.)F1632.8 GBF16165details
LLaDA2.1 mini16B (1.4B act.)F1631.3 GBF16327details
Moonlight 16B A3B Instruct16B (3.0B act.)F1630.7 GBF16156details
DeepSeek Coder V2 Lite Instruct16B (2.7B act.)F1630.1 GBF16176details
DeepSeek V2 Lite16B (2.7B act.)F1630.1 GBF16176details
DeepSeek V2 Lite Chat16B (2.7B act.)F1630.1 GBF16176details
Qwen2.5 Coder 14B Instruct15BF1629.7 GBF1632details
DeepSeek R1 Distill Qwen 14B15BF1629.7 GBF1632details
Qwen3 14B15BF1629.4 GBF1632details
phi 415BF1629.5 GBF1632details
gemma 3 12b it12BF1623.6 GBF1640details
Llama Guard 4 12B12BF1624.6 GBF1639details
Llama 3.2 11B Vision Instruct11BF1620.1 GBF1648details
Llama 3.2 11B Vision11BF1621.7 GBF1644details
GLM 4.6V Flash10BF1618.5 GBF1650details
GLM 4.1V 9B Thinking10BF1618.5 GBF1650details
Step3 VL 10B10BF1632.3 GBF1629details
SenseNova Loop 9B Preview9.7BF1617.8 GBF1652details
Qwen3.5 9B9.7BF1617.8 GBF1652details
Ornith 1.5 9B9.7BF1617.8 GBF1652details
Qwen3.5 9B Base9.7BF1617.8 GBF1652details
MiMo V2.6 Distill Qwen 9B9.4BF1617.8 GBF1652details
glm 4 9b9.4BF1623.2 GBF1650details
internlm3 8b instruct8.8BF1617.4 GBF1653details
granite 4.2 8b8.8BF1618.2 GBF1653details
granite 4.1 8b8.8BF1618.2 GBF1653details
Qwen3 VL 8B Instruct8.8BF1617.1 GBF1657details
Molmo2 8B8.7BF1617.1 GBF1657details
LFM2.5 8B A1B8.5B (1.0B act.)F1632.3 GBF16234details
Qwen2.5 VL 7B Instruct8.3BF1615.3 GBF1661details
UI TARS 1.5 7B8.3BF1615.3 GBF1661details
olmOCR 2 7B 10258.3BF1615.3 GBF1661details
olmOCR 7B 0225 preview8.3BF1616.6 GBF1656details
UI TARS 7B DPO8.3BF1615.3 GBF1661details
Qwen3 8B8.2BF1617.1 GBF1657details
DeepSeek R1 0528 Qwen3 8B8.2BF1617.1 GBF1657details
granite 3.3 8b instruct8.2BF1617.0 GBF1657details
granite 3.1 8b instruct8.2BF1617.0 GBF1657details
granite 3.2 8b instruct8.2BF1617.0 GBF1657details
Apertus 8B Instruct 25098.1BF1616.7 GBF1658details
Llama 3.1 8B Instruct8.0BF1616.6 GBF1658details
Llama 3.1 8B8.0BF1616.6 GBF1658details
Hermes 3 Llama 3.1 8B8.0BF1616.6 GBF1658details
DeepSeek R1 Distill Llama 8B8.0BF1631.6 GBF1629details
Meta Llama 3 8B Instruct8.0BF1616.6 GBF1658details
Meta Llama Guard 2 8B8.0BF1616.6 GBF1658details
Meta Llama 3.1 8B Instruct8.0BF1616.6 GBF1658details
Ling 3.0 tiny7.9B (1.4B act.)F1615.6 GBF16338details
MiMo 7B RL7.8BF1616.4 GBF1660details
internlm2 5 7b chat7.7BF1616.0 GBF1660details
internlm2 chat 7b7.7BF1616.0 GBF1660details
Qwen2.5 7B Instruct7.6BF1615.3 GBF1661details
Qwen2.5 Coder 7B Instruct7.6BF1615.3 GBF1661details
DeepSeek R1 Distill Qwen 7B7.6BF1615.3 GBF1661details
Falcon H1R 7B7.6BF1615.1 GBF1662details
Olmo 3 7B Instruct7.3BF1616.7 GBF1664details
Olmo 3 1025 7B7.3BF1616.7 GBF1664details
Olmo 3 7B Think7.3BF1616.7 GBF1664details
Mistral 7B v0.17.2BF1614.9 GBF1665details
Mistral 7B Instruct v0.27.2BF1614.9 GBF1665details
Mistral 7B Instruct v0.17.2BF1614.9 GBF1665details
falcon 7b7.2BF1618.4 GBF1665details
falcon 7b instruct7.2BF1618.4 GBF1665details
granite 4.0 h tiny6.9B (1.5B act.)F1613.6 GBF16319details
OLMoE 1B 7B 09246.9B (1.3B act.)F1614.4 GBF16365details
deepseek coder 7b instruct v1.56.9BF1617.2 GBF1668details
deepseek coder 6.7b instruct6.7BF1617.0 GBF1669details
deepseek coder 6.7b base6.7BF1617.0 GBF1669details
Llama 2 7b hf6.7BF1617.0 GBF1669details
Yi 6B 200K6.1BF1612.3 GBF1677details
Yi 6B6.1BF1612.3 GBF1677details
Molmo2 4B4.9BF1610.0 GBF16106details
WeVisOne VL 4B4.8BF1610.0 GBF16106details
Mage VL Cowork4.7BF1610.0 GBF16106details
Qianfan OCR4.7BF1610.1 GBF16106details
Qwen3.5 4B4.7BF169.0 GBF16111details
S5 nano4.7BF169.2 GBF16108details
LightOnOCR 3 4B4.5BF169.0 GBF16111details
SingVL S1 4B4.5BF169.0 GBF16111details
Intern Decision 4B4.5BF169.0 GBF16111details
Qwen3 VL 4B Instruct4.4BF169.3 GBF16116details
gemma 3 4b it4.3BF168.4 GBF16120details
medgemma 1.5 4b it4.3BF168.4 GBF16120details
medgemma 4b it4.3BF168.4 GBF16120details
gemma 3 4b pt4.3BF169.2 GBF16109details
Phi 3.5 vision instruct4.1BF1611.2 GBF16113details
Qwen3 4B4.0BF169.3 GBF16116details
Qwen3 4B Instruct 25074.0BF169.3 GBF16116details
granite vision 4.1 4b4.0BF167.6 GBF16137details
Phi 4 mini instruct3.8BF168.9 GBF16122details
Phi 3 mini 4k instruct3.8BF1610.6 GBF16122details
Phi 3.5 mini instruct3.8BF1610.6 GBF16122details
Phi 3 mini 128k instruct3.8BF1610.6 GBF16122details
Qwen2.5 VL 3B Instruct3.8BF166.7 GBF16151details
granite 4.2 3b3.7BF168.0 GBF16128details
granite 4.1 3b llmon preview3.7BF168.0 GBF16128details
Raon 1 nano3.5BF167.0 GBF16149details
granite 4.1 3b3.4BF167.6 GBF16137details
granite 4.0 micro3.4BF167.6 GBF16137details
DeepSeek OCR 23.4B (1.2B act.)F166.6 GBF16452details
deepseek vl2 tiny3.4B (1.2B act.)F167.4 GBF16398details
Unlimited OCR 23.3B (1.1B act.)F166.6 GBF16463details
Unlimited OCR3.3B (1.1B act.)F166.6 GBF16466details
DeepSeek OCR3.3B (1.1B act.)F166.6 GBF16466details
granite 3.1 3b a800m instruct3.3B (883M act.)F167.1 GBF16530details
Llama 3.2 3B Instruct3.2BF1613.5 GBF1673details
Llama 3.2 3B3.2BF167.5 GBF16146details
Hermes 3 Llama 3.2 3B3.2BF167.5 GBF16145details
d1 3B3.1BF1610.8 GBF1687details
LFM2.5 VL 3B3.1BF1610.8 GBF1687details
Qwen2.5 3B Instruct3.1BF166.7 GBF16152details
SmolLM3 3B3.1BF166.9 GBF16152details
SmolLM3 3B Base3.1BF166.9 GBF16152details
phi 22.8BF168.2 GBF16168details
LFM2.5 2.6B2.7BF1610.8 GBF1687details
granite 3.3 2b instruct2.5BF165.8 GBF16185details
MiniCPM5 2B2.5BF165.7 GBF16186details
WeVisOne VL 2B2.4BF165.4 GBF16230details
Qwen3.5 2B2.3BF164.5 GBF16248details
SmolVLM Instruct2.2BF165.4 GBF16258details
Qwen3 1.7B2.0BF164.8 GBF16272details
Qwen3.8 27B DSpine b162.0BF164.8 GBF16230details
d1 2B1.9BF167.2 GBF16135details
LFM3 VL 2B1.9BF167.2 GBF16135details
DeepSeek R1 Distill Qwen 1.5B1.8BF164.2 GBF16263details
LFM3 1.7B1.7BF167.2 GBF16135details
LFM3 1.7B Base1.7BF164.0 GBF16271details
SmolLM2 1.7B Instruct1.7BF165.2 GBF16273details
SmolLM2 1.7B1.7BF165.2 GBF16273details
SmolLM 1.7B1.7BF165.2 GBF16273details
granite 4.0 1b1.6BF164.3 GBF16286details
Qwen2.5 1.5B Instruct1.5BF163.8 GBF16303details
OLMo 2 0425 1B1.5BF164.4 GBF16315details
deepseek coder 1.3b instruct1.3BF164.5 GBF16348details
Llama 3.2 1B1.2BF163.2 GBF16379details
Llama 3.2 1B Instruct1.2BF165.5 GBF16189details
LFM2.5 1.2B Instruct1.2BF165.0 GBF16200details
HunyuanOCR1.1BF163.5 GBF16418details
PaddleOCR VL 1.6959MF162.5 GBF16488details
Qwen3.5 0.8B873MF162.4 GBF16617details
LightOnOCR 3 0.8B853MF162.4 GBF16617details
FastVLM 0.5B759MF162.2 GBF16617details
Qwen3 0.6B752MF162.7 GBF16781details
GOT OCR2 0716MF162.8 GBF16654details
Nemotron 3.5 Parse631MF161.9 GBF16716details
GOT OCR 2.0 hf561MF162.5 GBF16835details
SmolVLM2 500M Video Instruct507MF161.6 GBF161141details
SmolVLM 500M Instruct507MF161.6 GBF161141details
Qwen2.5 0.5B Instruct494MF161.7 GBF16947details
LFM2.5 VL 450M449MF161.9 GBF16658details
SmolLM2 360M Instruct362MF161.5 GBF161290details
SmolLM2 360M362MF161.5 GBF161290details
LFM2.5 350M354MF161.9 GBF16658details
LFM2 350M354MF161.4 GBF161320details

Just too big at 4-bit

These need up to 35% more memory than the 2x RTX 3090 has at Q4_K_M and 8K context. A smaller quant or shorter context may work.

ModelQ4_K_M needsShort by
Hunyuan A13B Instruct47.1 GB1.5 GB
Mistral 7B Instruct v0.247.7 GB2.1 GB
gpt oss safeguard 120b59.5 GB13.9 GB
gpt oss 120b59.5 GB13.9 GB
GLM 4.5V61.4 GB15.8 GB

Questions

What is the biggest model that runs on the 2x RTX 3090?

Of the models we track, the largest that fits at 8K context is Ling 3.0 flash (127B) at Q2_K, needing about 43.8 GB.

How much of the 2x RTX 3090's memory can a model use?

About 45.6 GB: we assume 95% of the 2× 24 GB is usable after driver and display overhead.

Spec source: NVIDIA specifications. Model data: Hugging Face Hub API. Speed is a bandwidth ceiling (bandwidth ÷ bytes read per token), not a benchmark. Methodology · Report an error.