RunsOnMy ModelsGPUs & MacsAPI pricesVRAM calculatorNew

What AI models run on the RTX PRO 6000 Blackwell?

The RTX PRO 6000 Blackwell has 96 GB of VRAM (1,792 GB/s). About 91.2 GB is usable for a model. 227 of 285 open models we track fit at 8K context.

227models fit (8K ctx)
227still fit at 32K ctx
241Blargest that fits
1792 GB/smemory bandwidth

Models that fit, largest first

ModelParamsBest quant (8K)Needs32K contextMax tok/s (est.)
Intern S1241B (28B act.)Q2_K86.2 GBQ2_K172details
DeepSeek V2 Chat236B (21B act.)Q2_K83.5 GBQ2_K224details
MiniMax M2.5229B (11B act.)Q2_K80.3 GBQ2_K446details
MiniMax M2.7229B (11B act.)Q2_K82.6 GBQ2_K433details
MiniMax M2229B (11B act.)Q2_K80.3 GBQ2_K446details
MiniMax M2.1229B (11B act.)Q2_K80.3 GBQ2_K446details
MiniMax M3.1 Flash220B (4.4B act.)Q2_K78.7 GBQ2_K—details
Step 3.7 Flash201BQ2_K74.5 GBQ2_K24details
Step 3.5 Flash199BQ2_K69.0 GBQ2_K26details
Qwen3.8 Flash Next180B (62B act.)Q2_K63.9 GBQ2_K78details
Ling 3.0 flash Sante127B (5.6B act.)Q4_K_M75.9 GBQ4_K_M507details
Ling 3.0 flash127B (5.6B act.)Q4_K_M73.5 GBQ4_K_M524details
Ornith 1.5 122B125B (13B act.)Q4_K_M72.3 GBQ4_K_M230details
gpt oss 120b117B (5.8B act.)F1661.9 GBF16557details
gpt oss safeguard 120b117B (5.8B act.)Q8_060.1 GBQ8_0574details
GLM 4.5 Air110B (15B act.)Q5_K_M79.9 GBQ4_K_M158details
Llama 4 Scout 17B 16E Instruct109B (18B act.)Q5_K_M73.6 GBQ5_K_M141details
Llama 4 Scout 17B 16E109B (18B act.)Q5_K_M74.4 GBQ5_K_M139details
GLM 4.5V108B (14B act.)Q5_K_M73.6 GBQ5_K_M176details
GLM 4.6V108B (14B act.)Q5_K_M77.3 GBQ5_K_M167details
Hunyuan A13B Instruct80B (13B act.)Q8_081.2 GBQ6_K130details
Kimi Dev 72B73BQ8_075.1 GBQ6_K23details
Llama 3.3 70B Instruct71BQ8_073.0 GBQ8_024details
DeepSeek R1 Distill Llama 70B71BQ8_073.0 GBQ8_024details
Llama 3.1 70B71BQ8_073.0 GBQ8_024details
Kimi Linear 48B A3B Instruct49B (3.0B act.)Q8_049.6 GBQ8_0562details
Nous Hermes 2 Mixtral 8x7B DPO47B (13B act.)Q8_047.7 GBQ8_0131details
falcon 40b42BF1679.4 GBQ8_021details
flint40B (1.3B act.)F1675.1 GBF16717details
Maxwell V1 Flash37B (2.3B act.)F1669.7 GBF16395details
Hermes 4.3 36B36BF1670.0 GBF1625details
Seed OSS 36B Instruct36BF1670.0 GBF1625details
Qwen3.6 35B A3B36B (3.0B act.)F1667.2 GBF16302details
Ornith 1.5 35B A3B36B (3.0B act.)F1667.2 GBF16302details
Qwen3.5 35B A3B36B (3.0B act.)F1665.6 GBF16310details
Axion 1.0 35B35B (3.9B act.)F1665.6 GBF16232details
Qwen AgentWorld 35B A3B35B (3.0B act.)F1665.6 GBF16298details
Yi 34B 200K34BF1666.5 GBF1626details
Yi 34B34BF1666.5 GBF1626details
Yi 34B Chat34BF1666.5 GBF1626details
Yi 1.5 34B Chat34BF1666.5 GBF1626details
Nous Hermes 2 Yi 34B34BF1666.5 GBF1626details
DeepSeek R1 Distill Qwen 32B33BF1663.7 GBF1627details
Qwen3 32B33BF1663.7 GBF1627details
GLM Z1 32B 041433BF1661.8 GBF1628details
GLM 4 32B 041433BF1661.8 GBF1628details
granite 4.0 h small32B (8.8B act.)F1660.7 GBF16102details
gemma 4 31B it31BF1660.1 GBF1629details
GLM 4.7 Flash31B (4.6B act.)F1656.9 GBF16203details
Qwen3 Coder 30B A3B Instruct31B (3.0B act.)F1658.3 GBF16299details
North Mini Code 1.030B (3.3B act.)F1658.2 GBF16271details
Hy Memory 30B A3B30B (3.0B act.)F1657.4 GBF16299details
Muse Glimmer 30B30BF1652.9 GBF1632details
granite 4.2 30b29BF1657.1 GBF1631details
Qwen3.8 27B28BF1652.3 GBF1633details
Qwen3.6 27B28BF1651.5 GBF1633details
Qwen3.5 27B28BF1651.5 GBF1633details
gemma 3 27b it27BF1652.2 GBF1633details
Arete 27B27BF1651.5 GBF1633details
MiniMax H3 Image PE27BF1652.3 GBF1633details
Trinity Mini26B (2.0B act.)F1649.7 GBF16456details
GLiDE 27B26BF1650.0 GBF1634details
diffusiongemma 26B A4B it26B (4.0B act.)F1648.5 GBF16229details
gemma 4 26B A4B it26B (4.0B act.)F1648.4 GBF16229details
LFM2.5 24B A2B24B (2.0B act.)Q8_024.5 GBQ8_0843details
ERNIE 4.5 21B A3B PT22BF1641.7 GBF1641details
ERNIE 4.5 21B A3B Thinking22BF1641.7 GBF1641details
gpt oss safeguard 20b22B (4.8B act.)F1613.8 GBF16583details
gpt oss 20b21B (4.2B act.)F1613.8 GBF16648details
Groot 19B A3B 26102319B (3.0B act.)F1636.4 GBF16305details
Kimi VL A3B Thinking 250616B (3.0B act.)F1660.4 GBF16153details
Kimi VL A3B Instruct16B (3.0B act.)F1631.5 GBF16299details
Kimi VL A3B Thinking16B (3.0B act.)F1631.5 GBF16299details
deepseek moe 16b base16B (2.8B act.)F1632.8 GBF16317details
LLaDA2.1 mini16B (1.4B act.)F1631.3 GBF16625details
Moonlight 16B A3B Instruct16B (3.0B act.)F1630.7 GBF16299details
DeepSeek Coder V2 Lite Instruct16B (2.7B act.)F1630.1 GBF16337details
DeepSeek V2 Lite16B (2.7B act.)F1630.1 GBF16337details
DeepSeek V2 Lite Chat16B (2.7B act.)F1630.1 GBF16337details
Qwen2.5 Coder 14B Instruct15BF1629.7 GBF1661details
DeepSeek R1 Distill Qwen 14B15BF1629.7 GBF1661details
Qwen3 14B15BF1629.4 GBF1661details
phi 415BF1629.5 GBF1661details
gemma 3 12b it12BF1623.6 GBF1676details
Llama Guard 4 12B12BF1624.6 GBF1675details
Llama 3.2 11B Vision Instruct11BF1620.1 GBF1692details
Llama 3.2 11B Vision11BF1621.7 GBF1684details
GLM 4.6V Flash10BF1618.5 GBF1695details
GLM 4.1V 9B Thinking10BF1618.5 GBF1695details
Step3 VL 10B10BF1632.3 GBF1655details
SenseNova Loop 9B Preview9.7BF1617.8 GBF16100details
Qwen3.5 9B9.7BF1617.8 GBF16100details
Ornith 1.5 9B9.7BF1617.8 GBF16100details
Qwen3.5 9B Base9.7BF1617.8 GBF16100details
MiMo V2.6 Distill Qwen 9B9.4BF1617.8 GBF16100details
glm 4 9b9.4BF1623.2 GBF1695details
internlm3 8b instruct8.8BF1617.4 GBF16102details
granite 4.2 8b8.8BF1618.2 GBF16102details
granite 4.1 8b8.8BF1618.2 GBF16102details
Qwen3 VL 8B Instruct8.8BF1617.1 GBF16109details
Molmo2 8B8.7BF1617.1 GBF16109details
LFM2.5 8B A1B8.5B (1.0B act.)F1632.3 GBF16448details
Qwen2.5 VL 7B Instruct8.3BF1615.3 GBF16118details
UI TARS 1.5 7B8.3BF1615.3 GBF16118details
olmOCR 2 7B 10258.3BF1615.3 GBF16118details
olmOCR 7B 0225 preview8.3BF1616.6 GBF16108details
UI TARS 7B DPO8.3BF1615.3 GBF16118details
Qwen3 8B8.2BF1617.1 GBF16109details
DeepSeek R1 0528 Qwen3 8B8.2BF1617.1 GBF16109details
granite 3.3 8b instruct8.2BF1617.0 GBF16110details
granite 3.1 8b instruct8.2BF1617.0 GBF16110details
granite 3.2 8b instruct8.2BF1617.0 GBF16110details
Apertus 8B Instruct 25098.1BF1616.7 GBF16111details
Llama 3.1 8B Instruct8.0BF1616.6 GBF16112details
Llama 3.1 8B8.0BF1616.6 GBF16112details
Hermes 3 Llama 3.1 8B8.0BF1616.6 GBF16112details
DeepSeek R1 Distill Llama 8B8.0BF1631.6 GBF1656details
Meta Llama 3 8B Instruct8.0BF1616.6 GBF16112details
Meta Llama Guard 2 8B8.0BF1616.6 GBF16112details
Meta Llama 3.1 8B Instruct8.0BF1616.6 GBF16112details
Ling 3.0 tiny7.9B (1.4B act.)F1615.6 GBF16648details
MiMo 7B RL7.8BF1616.4 GBF16114details
internlm2 5 7b chat7.7BF1616.0 GBF16116details
internlm2 chat 7b7.7BF1616.0 GBF16116details
Qwen2.5 7B Instruct7.6BF1615.3 GBF16118details
Qwen2.5 Coder 7B Instruct7.6BF1615.3 GBF16118details
DeepSeek R1 Distill Qwen 7B7.6BF1615.3 GBF16118details
Falcon H1R 7B7.6BF1615.1 GBF16118details
Olmo 3 7B Instruct7.3BF1616.7 GBF16123details
Olmo 3 1025 7B7.3BF1616.7 GBF16123details
Olmo 3 7B Think7.3BF1616.7 GBF16123details
Mistral 7B v0.17.2BF1614.9 GBF16124details
Mistral 7B Instruct v0.27.2BF1614.9 GBF16124details
Mistral 7B Instruct v0.17.2BF1614.9 GBF16124details
falcon 7b7.2BF1618.4 GBF16124details
falcon 7b instruct7.2BF1618.4 GBF16124details
granite 4.0 h tiny6.9B (1.5B act.)F1613.6 GBF16611details
OLMoE 1B 7B 09246.9B (1.3B act.)F1614.4 GBF16699details
deepseek coder 7b instruct v1.56.9BF1617.2 GBF16130details
deepseek coder 6.7b instruct6.7BF1617.0 GBF16133details
deepseek coder 6.7b base6.7BF1617.0 GBF16133details
Llama 2 7b hf6.7BF1617.0 GBF16133details
Yi 6B 200K6.1BF1612.3 GBF16148details
Yi 6B6.1BF1612.3 GBF16148details
Molmo2 4B4.9BF1610.0 GBF16203details
WeVisOne VL 4B4.8BF1610.0 GBF16203details
Mage VL Cowork4.7BF1610.0 GBF16203details
Qianfan OCR4.7BF1610.1 GBF16203details
Qwen3.5 4B4.7BF169.0 GBF16213details
S5 nano4.7BF169.2 GBF16207details
LightOnOCR 3 4B4.5BF169.0 GBF16213details
SingVL S1 4B4.5BF169.0 GBF16213details
Intern Decision 4B4.5BF169.0 GBF16213details
Qwen3 VL 4B Instruct4.4BF169.3 GBF16223details
gemma 3 4b it4.3BF168.4 GBF16231details
medgemma 1.5 4b it4.3BF168.4 GBF16231details
medgemma 4b it4.3BF168.4 GBF16231details
gemma 3 4b pt4.3BF169.2 GBF16208details
Phi 3.5 vision instruct4.1BF1611.2 GBF16216details
Qwen3 4B4.0BF169.3 GBF16223details
Qwen3 4B Instruct 25074.0BF169.3 GBF16223details
granite vision 4.1 4b4.0BF167.6 GBF16263details
Phi 4 mini instruct3.8BF168.9 GBF16233details
Phi 3 mini 4k instruct3.8BF1610.6 GBF16234details
Phi 3.5 mini instruct3.8BF1610.6 GBF16234details
Phi 3 mini 128k instruct3.8BF1610.6 GBF16234details
Qwen2.5 VL 3B Instruct3.8BF166.7 GBF16290details
granite 4.2 3b3.7BF168.0 GBF16245details
granite 4.1 3b llmon preview3.7BF168.0 GBF16245details
Raon 1 nano3.5BF167.0 GBF16286details
granite 4.1 3b3.4BF167.6 GBF16263details
granite 4.0 micro3.4BF167.6 GBF16263details
DeepSeek OCR 23.4B (1.2B act.)F166.6 GBF16866details
deepseek vl2 tiny3.4B (1.2B act.)F167.4 GBF16762details
Unlimited OCR 23.3B (1.1B act.)F166.6 GBF16886details
Unlimited OCR3.3B (1.1B act.)F166.6 GBF16892details
DeepSeek OCR3.3B (1.1B act.)F166.6 GBF16892details
granite 3.1 3b a800m instruct3.3B (883M act.)F167.1 GBF161014details
Llama 3.2 3B Instruct3.2BF1613.5 GBF16139details
Llama 3.2 3B3.2BF167.5 GBF16279details
Hermes 3 Llama 3.2 3B3.2BF167.5 GBF16279details
d1 3B3.1BF1610.8 GBF16166details
LFM2.5 VL 3B3.1BF1610.8 GBF16166details
Qwen2.5 3B Instruct3.1BF166.7 GBF16290details
SmolLM3 3B3.1BF166.9 GBF16291details
SmolLM3 3B Base3.1BF166.9 GBF16291details
phi 22.8BF168.2 GBF16322details
LFM2.5 2.6B2.7BF1610.8 GBF16166details
granite 3.3 2b instruct2.5BF165.8 GBF16354details
MiniCPM5 2B2.5BF165.7 GBF16356details
WeVisOne VL 2B2.4BF165.4 GBF16440details
Qwen3.5 2B2.3BF164.5 GBF16475details
SmolVLM Instruct2.2BF165.4 GBF16494details
Qwen3 1.7B2.0BF164.8 GBF16520details
Qwen3.8 27B DSpine b162.0BF164.8 GBF16441details
d1 2B1.9BF167.2 GBF16258details
LFM3 VL 2B1.9BF167.2 GBF16258details
DeepSeek R1 Distill Qwen 1.5B1.8BF164.2 GBF16503details
LFM3 1.7B1.7BF167.2 GBF16258details
LFM3 1.7B Base1.7BF164.0 GBF16518details
SmolLM2 1.7B Instruct1.7BF165.2 GBF16523details
SmolLM2 1.7B1.7BF165.2 GBF16524details
SmolLM 1.7B1.7BF165.2 GBF16523details
granite 4.0 1b1.6BF164.3 GBF16548details
Qwen2.5 1.5B Instruct1.5BF163.8 GBF16580details
OLMo 2 0425 1B1.5BF164.4 GBF16603details
deepseek coder 1.3b instruct1.3BF164.5 GBF16665details
Llama 3.2 1B1.2BF163.2 GBF16725details
Llama 3.2 1B Instruct1.2BF165.5 GBF16361details
LFM2.5 1.2B Instruct1.2BF165.0 GBF16382details
HunyuanOCR1.1BF163.5 GBF16800details
PaddleOCR VL 1.6959MF162.5 GBF16935details
Qwen3.5 0.8B873MF162.4 GBF161181details
LightOnOCR 3 0.8B853MF162.4 GBF161181details
FastVLM 0.5B759MF162.2 GBF161181details
Qwen3 0.6B752MF162.7 GBF161496details
GOT OCR2 0716MF162.8 GBF161251details
Nemotron 3.5 Parse631MF161.9 GBF161371details
GOT OCR 2.0 hf561MF162.5 GBF161598details
SmolVLM2 500M Video Instruct507MF161.6 GBF162184details
SmolVLM 500M Instruct507MF161.6 GBF162184details
Qwen2.5 0.5B Instruct494MF161.7 GBF161814details
LFM2.5 VL 450M449MF161.9 GBF161259details
SmolLM2 360M Instruct362MF161.5 GBF162470details
SmolLM2 360M362MF161.5 GBF162470details
LFM2.5 350M354MF161.9 GBF161259details
LFM2 350M354MF161.4 GBF162528details

Just too big at 4-bit

These need up to 35% more memory than the RTX PRO 6000 Blackwell has at Q4_K_M and 8K context. A smaller quant or shorter context may work.

ModelQ4_K_M needsShort by
Qwen3.8 Flash Next103.5 GB12.3 GB
Step 3.5 Flash115.9 GB24.7 GB
Step 3.7 Flash118.8 GB27.6 GB

Questions

What is the biggest model that runs on the RTX PRO 6000 Blackwell?

Of the models we track, the largest that fits at 8K context is Intern S1 (241B) at Q2_K, needing about 86.2 GB.

How much of the RTX PRO 6000 Blackwell's memory can a model use?

About 91.2 GB: we assume 95% of the 96 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.