Skip to content

What can the RTX 6000 Ada run?

What fits on the RTX 6000 Ada
Text models: 184Visual models: 12Strongest first
Memory
48 GB
Bandwidth
960 GB/s
Maker
NVIDIA

Open the calculator on this machineEvery model for 48 GB of VRAM

Text models that run on it

Text models that run on the RTX 6000 Ada, best first
ModelBest fitContextSpeedStrongest at
Qwen3.8 27B8-bit256K23 tok/sChat, Coding, Agents, Docs
Muse Glimmer 30B8-bit128K21 tok/sDocs
Qwen3.5 122B A10B2-bit32K115 tok/sChat, Coding, Agents, Docs
Nemotron 3 Super 120B A12B2-bit184K82 tok/sChat, Coding, Agents, Docs
Nemotron 3.5 Bolt 74B A9B4-bit256K73 tok/sChat, Coding, Agents, Docs
Qwen3.6 35B A3B8-bit256K138 tok/sChat, Coding, Agents, Docs
Gemma 4 31B8-bit256K20 tok/sChat, Coding, Agents, Docs
Gemma 4 26B A4B8-bit256K128 tok/sChat, Coding, Agents, Docs
GLM-4.7 Flash8-bit198K132 tok/sChat, Coding, Agents
Gemma 4 12B8-bit256K49 tok/sChat, Coding, Docs
Mistral Small 4 119B2-bit136K173 tok/sChat, Docs
gpt-oss 120B2-bit104K200 tok/sChat, Coding
Qwen3 Coder Next 80B3-bit256K193 tok/sCoding, Agents
Nemotron 3.5 Lightning 30B A3B8-bit256K126 tok/sAgents, Docs
Devstral Small 2 24BFP8128K26 tok/sCoding
LFM2.5 24B A2B8-bit128K180 tok/sAgents
Mistral Small 3.2 24B8-bit128K26 tok/sChat, Coding, Agents
Ministral 3 14B8-bit192K45 tok/sCoding, Agents, Docs
gpt-oss 20BMXFP4128K190 tok/sAgents
Ministral 3 8B8-bit256K70 tok/sDocs
Llama 3.3 70B3-bit36K19 tok/sChat, Coding, Agents, Docs
Olmo 3.1 32B8-bit64K19 tok/sChat, Coding, Agents, Docs
Llama 3.1 8B8-bit128K78 tok/sChat, Coding, Agents, Docs
Qwen3 14B8-bit40K43 tok/sNot rated
Qwen3 VL 8B Instruct8-bit256K72 tok/sText and images
Qwen3 8B8-bit40K77 tok/sNot rated
Qwen3 32B8-bit40K19 tok/sNot rated
Qwen3.6 27B8-bit256K23 tok/sText and images
Qwen2.5 Coder 14B Instruct8-bit32K42 tok/sCoding
Qwen3 Coder 30B A3B Instruct8-bit152K131 tok/sCoding
Qwen3.5 27B8-bit256K23 tok/sText and images
Qwen3.5 35B A3B8-bit256K138 tok/sText and images
NVIDIA Nemotron 3 Nano 30B A3B BF168-bit256K126 tok/sNot rated
GLM 4.5 Air2-bit32K90 tok/sNot rated
Qwen3 30B A3B8-bit40K131 tok/sNot rated
Qwen3 30B A3B Instruct 25078-bit152K131 tok/sNot rated
Laguna XS.28-bit256K139 tok/sNot rated
OTel 2.0 LLM 31B IT8-bit256K20 tok/sNot rated
Qwen2.5 32B Instruct8-bit32K19 tok/sNot rated
MiniCPM V 4.7 35B A3B8-bit256K138 tok/sText and images
Qwen2.5 14B Instruct8-bit32K42 tok/sNot rated
Laguna XS 2.18-bit256K139 tok/sNot rated
Diffusiongemma 26B A4B IT8-bit256K123 tok/sText and images
Qwen2.5 VL 32B Instruct8-bit44K19 tok/sText and images
Qwen2.5 Coder 32B Instruct8-bit32K19 tok/sCoding
Laguna S 2.12-bit72K132 tok/sNot rated
Qwen3 VL 30B A3B Instruct8-bit144K131 tok/sText and images
EXAONE 3.5 7.8B Instruct8-bit32K79 tok/sNot rated
DeepSeek R1 0528 Qwen3 8B8-bit128K77 tok/sNot rated
Gemma 3 12B IT8-bit128K52 tok/sText and images
Phi 3.5 Mini Instruct8-bit104K146 tok/sNot rated
DeepSeek R1 Distill Qwen 32B8-bit48K19 tok/sNot rated
Gemma 3 27B IT8-bit128K23 tok/sText and images
Ornith 1.5 35B A3B8-bit256K138 tok/sNot rated
Ornith 1.5 122B2-bit32K98 tok/sNot rated
GPT Neox 20B8-bit2K30 tok/sNot rated
Apertus 8B Instruct 25098-bit64K78 tok/sNot rated
Phi 48-bit16K42 tok/sNot rated
Phi 3 Mini 128K Instruct8-bit104K146 tok/sNot rated
Qwen3 VL 32B Instruct8-bit44K19 tok/sText and images

Best fit is the highest quality, up to 8-bit, that leaves the use case’s context. Ranked by our use-case scores, then by Hugging Face downloads. Speeds are rough, plus or minus 25%. The top 60 of 184 are shown.

Image and video models

Image and video models that run on the RTX 6000 Ada
ModelBest fitPer outputStrongest at
MiniMax H316-bit2.9 minVideo
LTX-2.516-bit36 sVideo
FLUX.1 [dev]16-bit5.9 sImages
Qwen-Image16-bit1.6 minImages
FLUX.2 [dev]8-bit43 sImages
Wan2.2 I2V A14B16-bit14 minVideo
Wan2.1 I2V 14B16-bit14 minVideo
Wan 2.1 T2V-14B16-bit18 minVideo
Krea 2 Turbo16-bit5.9 sImages
Qwen Image 251216-bit1.6 minImages
Wan 2.2 A14B16-bit14 minVideo
HunyuanVideo 1.516-bit17 minVideo

Only just too big

These need up to a quarter more memory than the RTX 6000 Ada has. Spilling into system RAM or a lower precision can get them running, slowly.

Questions

What is the best LLM for the RTX 6000 Ada?

Of the open models we track, the strongest that run well on the RTX 6000 Ada are Qwen3.8 27B, Muse Glimmer 30B, Qwen3.5 122B A10B. 184 text models fit it in all.

Calculated from published specs, not benchmarked. All machines