Skip to content

What can the Ryzen AI Max+ 395 128 GB run?

What fits on the Ryzen AI Max+ 395 128 GB
Text models: 119Visual models: 9Strongest first
Memory
128 GB unified
Bandwidth
256 GB/s
Maker
AMD
Also called
Strix Halo

Open the calculator on this machineRyzen AI Max+ 395 (Strix Halo) in our inventory

Text models that run on it

Text models that run on the Ryzen AI Max+ 395 128 GB, best first
ModelBest fitContextSpeedStrongest at
Qwen3.8 Flash-Next3-bit256K41 tok/sChat, Coding, Agents
MiniMax M31.6-bit64K28 tok/sDocs
Qwen3.8 27B8-bit256K5.3 tok/sChat, Coding, Agents, Docs
Qwen3.5 397B A17B1.6-bit256K34 tok/sAgents, Docs
MiniMax M2.72-bit40K33 tok/sCoding, Agents
Muse Glimmer 30B8-bit128K5.0 tok/sDocs
Mistral Medium 3.5 128B5-bit16K1.7 tok/sChat, Coding, Agents, Docs
Qwen3.5 122B A10B5-bit256K19 tok/sChat, Coding, Agents, Docs
Nemotron 3 Super 120B A12B5-bit256K15 tok/sChat, Coding, Agents, Docs
Nemotron 3.5 Bolt 74B A9B8-bit256K14 tok/sChat, Coding, Agents, Docs
Qwen3.6 35B A3B8-bit256K40 tok/sChat, Coding, Agents, Docs
Gemma 4 31B8-bit256K4.6 tok/sChat, Coding, Agents, Docs
Gemma 4 26B A4B8-bit256K34 tok/sChat, Coding, Agents, Docs
GLM-4.7 Flash8-bit198K40 tok/sChat, Coding, Agents
Mistral Small 4 119B5-bit256K30 tok/sChat, Docs
gpt-oss 120BMXFP4128K37 tok/sChat, Coding
Qwen3 Coder Next 80B8-bit256K39 tok/sCoding, Agents
Nemotron 3.5 Lightning 30B A3B8-bit256K39 tok/sAgents, Docs
Devstral Small 2 24BFP8384K6.1 tok/sCoding
LFM2.5 24B A2B8-bit128K57 tok/sAgents
Mistral Small 3.2 24B8-bit128K6.1 tok/sChat, Coding, Agents
Llama 3.3 70B8-bit64K2.1 tok/sChat, Coding, Agents, Docs
Olmo 3.1 32B8-bit64K4.5 tok/sChat, Coding, Agents, Docs
Qwen3 32B8-bit40K4.5 tok/sNot rated
Qwen3.6 27B8-bit256K5.3 tok/sText and images
Qwen3 Coder 30B A3B Instruct8-bit256K40 tok/sCoding
Qwen3.5 27B8-bit256K5.3 tok/sText and images
Qwen3.5 35B A3B8-bit256K40 tok/sText and images
NVIDIA Nemotron 3 Nano 30B A3B BF168-bit256K39 tok/sNot rated
GLM 4.5 Air6-bit32K12 tok/sNot rated
Inkling Small2-bit4K32 tok/sText and images
Qwen3 30B A3B8-bit40K40 tok/sNot rated
MiniMax M2.52-bit40K30 tok/sNot rated
Qwen3 30B A3B Instruct 25078-bit256K40 tok/sNot rated
Laguna XS.28-bit256K41 tok/sNot rated
OTel 2.0 LLM 31B IT8-bit256K4.6 tok/sNot rated
Laguna M.12-bit40K16 tok/sNot rated
Qwen2.5 32B Instruct8-bit32K4.5 tok/sNot rated
MiniCPM V 4.7 35B A3B8-bit256K40 tok/sText and images
Laguna XS 2.18-bit256K41 tok/sNot rated
Diffusiongemma 26B A4B IT8-bit256K33 tok/sText and images
Qwen2.5 VL 32B Instruct8-bit125K4.4 tok/sText and images
Qwen2.5 Coder 32B Instruct8-bit32K4.5 tok/sCoding
Laguna S 2.16-bit16K20 tok/sNot rated
Qwen3 VL 30B A3B Instruct8-bit256K40 tok/sText and images
DeepSeek R1 Distill Qwen 32B8-bit128K4.5 tok/sNot rated
Gemma 3 27B IT8-bit128K5.5 tok/sText and images
Qwen3 VL 235B A22B Instruct2-bit44K16 tok/sText and images
Qwen3 235B A22B2-bit40K16 tok/sNot rated
Ornith 1.5 35B A3B8-bit256K40 tok/sNot rated
Ornith 1.5 122B5-bit256K16 tok/sNot rated
Ornith 1.5 397B1.6-bit256K25 tok/sNot rated
Qwen3 VL 32B Instruct8-bit224K4.4 tok/sText and images
Step 3.5 Flash2-bit52K37 tok/sNot rated
Qwen2.5 72B Instruct8-bit32K2.0 tok/sNot rated
Qwen3 Next 80B A3B Instruct8-bit256K39 tok/sNot rated
Llama 4 Scout 17B 16E Instruct6-bit36K9.9 tok/sText and images
MiniMax M22-bit40K30 tok/sNot rated
Qwen2.5 VL 72B Instruct8-bit56K2.0 tok/sText and images
Qwen1.5 7B8-bit32K20 tok/sNot rated

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 119 are shown.

Image and video models

Image and video models that run on the Ryzen AI Max+ 395 128 GB
ModelBest fitPer outputStrongest at
MiniMax H316-bit28 minVideo
LTX-2.516-bit3.1 minVideo
Qwen-Image16-bit17 minImages
FLUX.2 [dev]16-bit7.3 minImages
Wan2.2 I2V A14B16-bit2.4 hVideo
Wan2.1 I2V 14B16-bit2.4 hVideo
Wan 2.1 T2V-14B16-bit3.1 hVideo
Qwen Image 251216-bit17 minImages
Wan 2.2 A14B16-bit2.4 hVideo

Only just too big

These need up to a quarter more memory than the Ryzen AI Max+ 395 128 GB has. Spilling into system RAM or a lower precision can get them running, slowly.

Questions

What is the best LLM for the Ryzen AI Max+ 395 128 GB?

Of the open models we track, the strongest that run well on the Ryzen AI Max+ 395 128 GB are Qwen3.8 Flash-Next, MiniMax M3, Qwen3.8 27B. 119 text models fit it in all.

Calculated from published specs, not benchmarked. All machines