What can the Ryzen AI Max+ 395 64 GB run?
| Text models: 181 | Visual models: 20 | Strongest first |
- Memory
- 64 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
| Model | Best fit | Context | Speed | Strongest at |
|---|---|---|---|---|
| Qwen3.8 27B | 8-bit | 256K | 5.3 tok/s | Chat, Coding, Agents, Docs |
| Muse Glimmer 30B | 8-bit | 128K | 5.0 tok/s | Docs |
| Qwen3.5 122B A10B | 2-bit | 40K | 34 tok/s | Chat, Coding, Agents, Docs |
| Nemotron 3 Super 120B A12B | 2-bit | 208K | 26 tok/s | Chat, Coding, Agents, Docs |
| Nemotron 3.5 Bolt 74B A9B | 4-bit | 256K | 22 tok/s | Chat, Coding, Agents, Docs |
| Qwen3.6 35B A3B | 8-bit | 256K | 40 tok/s | Chat, Coding, Agents, Docs |
| Gemma 4 31B | 8-bit | 256K | 4.6 tok/s | Chat, Coding, Agents, Docs |
| Gemma 4 26B A4B | 8-bit | 256K | 34 tok/s | Chat, Coding, Agents, Docs |
| GLM-4.7 Flash | 8-bit | 198K | 40 tok/s | Chat, Coding, Agents |
| Gemma 4 12B | 8-bit | 256K | 12 tok/s | Chat, Coding, Docs |
| Mistral Small 4 119B | 2-bit | 144K | 52 tok/s | Chat, Docs |
| gpt-oss 120B | 2-bit | 112K | 64 tok/s | Chat, Coding |
| Qwen3 Coder Next 80B | 3-bit | 256K | 70 tok/s | Coding, Agents |
| Nemotron 3.5 Lightning 30B A3B | 8-bit | 256K | 39 tok/s | Agents, Docs |
| Devstral Small 2 24B | FP8 | 128K | 6.1 tok/s | Coding |
| LFM2.5 24B A2B | 8-bit | 128K | 57 tok/s | Agents |
| Mistral Small 3.2 24B | 8-bit | 128K | 6.1 tok/s | Chat, Coding, Agents |
| Ministral 3 14B | 8-bit | 192K | 11 tok/s | Coding, Agents, Docs |
| gpt-oss 20B | MXFP4 | 128K | 53 tok/s | Agents |
| Ministral 3 8B | 8-bit | 256K | 17 tok/s | Docs |
| Llama 3.3 70B | 4-bit | 16K | 3.6 tok/s | Chat, Coding, Agents, Docs |
| Olmo 3.1 32B | 8-bit | 64K | 4.5 tok/s | Chat, Coding, Agents, Docs |
| Llama 3.1 8B | 8-bit | 128K | 19 tok/s | Chat, Coding, Agents, Docs |
| Qwen3 14B | 8-bit | 40K | 10 tok/s | Not rated |
| Qwen3 VL 8B Instruct | 8-bit | 256K | 17 tok/s | Text and images |
| Qwen3 8B | 8-bit | 40K | 18 tok/s | Not rated |
| Qwen3 32B | 8-bit | 40K | 4.5 tok/s | Not rated |
| Qwen3.6 27B | 8-bit | 256K | 5.3 tok/s | Text and images |
| Qwen2.5 Coder 14B Instruct | 8-bit | 32K | 10 tok/s | Coding |
| Qwen3 Coder 30B A3B Instruct | 8-bit | 152K | 40 tok/s | Coding |
| Qwen3.5 27B | 8-bit | 256K | 5.3 tok/s | Text and images |
| Qwen3.5 35B A3B | 8-bit | 256K | 40 tok/s | Text and images |
| NVIDIA Nemotron 3 Nano 30B A3B BF16 | 8-bit | 256K | 39 tok/s | Not rated |
| GLM 4.5 Air | 2-bit | 32K | 25 tok/s | Not rated |
| Qwen3 30B A3B | 8-bit | 40K | 40 tok/s | Not rated |
| Qwen3 30B A3B Instruct 2507 | 8-bit | 152K | 40 tok/s | Not rated |
| Laguna XS.2 | 8-bit | 256K | 41 tok/s | Not rated |
| OTel 2.0 LLM 31B IT | 8-bit | 256K | 4.6 tok/s | Not rated |
| Qwen2.5 32B Instruct | 8-bit | 32K | 4.5 tok/s | Not rated |
| MiniCPM V 4.7 35B A3B | 8-bit | 256K | 40 tok/s | Text and images |
| Qwen2.5 14B Instruct | 8-bit | 32K | 10 tok/s | Not rated |
| Laguna XS 2.1 | 8-bit | 256K | 41 tok/s | Not rated |
| Diffusiongemma 26B A4B IT | 8-bit | 256K | 33 tok/s | Text and images |
| Qwen2.5 VL 32B Instruct | 8-bit | 44K | 4.4 tok/s | Text and images |
| Qwen2.5 Coder 32B Instruct | 8-bit | 32K | 4.5 tok/s | Coding |
| Laguna S 2.1 | 2-bit | 80K | 40 tok/s | Not rated |
| Qwen3 VL 30B A3B Instruct | 8-bit | 144K | 40 tok/s | Text and images |
| EXAONE 3.5 7.8B Instruct | 8-bit | 32K | 19 tok/s | Not rated |
| DeepSeek R1 0528 Qwen3 8B | 8-bit | 128K | 18 tok/s | Not rated |
| Gemma 3 12B IT | 8-bit | 128K | 13 tok/s | Text and images |
| Phi 3.5 Mini Instruct | 8-bit | 104K | 37 tok/s | Not rated |
| DeepSeek R1 Distill Qwen 32B | 8-bit | 48K | 4.5 tok/s | Not rated |
| Gemma 3 27B IT | 8-bit | 128K | 5.5 tok/s | Text and images |
| Ornith 1.5 35B A3B | 8-bit | 256K | 40 tok/s | Not rated |
| Ornith 1.5 122B | 2-bit | 40K | 27 tok/s | Not rated |
| GPT Neox 20B | 8-bit | 2K | 7.0 tok/s | Not rated |
| Apertus 8B Instruct 2509 | 8-bit | 64K | 19 tok/s | Not rated |
| Phi 4 | 8-bit | 16K | 10 tok/s | Not rated |
| Phi 3 Mini 128K Instruct | 8-bit | 104K | 37 tok/s | Not rated |
| Qwen3 VL 32B Instruct | 8-bit | 44K | 4.4 tok/s | Text 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 181 are shown.
Image and video models
| Model | Best fit | Per output | Strongest at |
|---|---|---|---|
| MiniMax H3 | 4-bit | 32 min | Video |
| LTX-2.5 | 8-bit | 3.1 min | Video |
| Z-Image Turbo | 16-bit | 27 s | Images |
| FLUX.1 [dev] | 16-bit | 53 s | Images |
| Qwen-Image | 8-bit | 17 min | Images |
| FLUX.2 [dev] | 5-bit | 8.4 min | Images |
| Qwen-Image 2.1 | 16-bit | 7.1 min | Images |
| FLUX.3 Klein | 16-bit | 39 s | Images |
| Wan2.2 I2V A14B | 16-bit | 2.4 h | Video |
| FLUX.2 [klein] 9B | 16-bit | 13 s | Images |
| Wan2.1 I2V 14B | 16-bit | 2.4 h | Video |
| Wan 2.1 T2V-14B | 16-bit | 3.1 h | Video |
| Krea 2 Turbo | 16-bit | 52 s | Images |
| Stable Diffusion 3.5 Large | 16-bit | 3.7 min | Images |
| Qwen Image 2512 | 8-bit | 17 min | Images |
| MOSS-Image | 16-bit | 4.6 min | Images |
| Wan 2.2 TI2V-5B | 16-bit | 40 min | Video |
| MOSS Image Base | 16-bit | 4.6 min | Images |
| Wan 2.2 A14B | 16-bit | 2.4 h | Video |
| HunyuanVideo 1.5 | 16-bit | 3.0 h | Video |
Only just too big
These need up to a quarter more memory than the Ryzen AI Max+ 395 64 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 64 GB?
Of the open models we track, the strongest that run well on the Ryzen AI Max+ 395 64 GB are Qwen3.8 27B, Muse Glimmer 30B, Qwen3.5 122B A10B. 181 text models fit it in all.
Calculated from published specs, not benchmarked. All machines