Can I run it?
Can I run Qwen3.8 35B A3B Distill on AMD Ryzen AI Max+ 395?
Runs
Runs fully in unified memory on your AMD Ryzen AI Max+ 395 at Q8_0, 8K context, about 9.1–12 tok/s. Weights 35.2 GB plus 0.19 GB of KV cache — 36.0 GB of 48.0 GB usable. Up to 256K context still fits.
Best quantQ8_0
Working context8K
Max that fits256K
Speed9.1–12 tok/sEstimate from memory bandwidth, not a benchmark. Method.
Weights35.2 GB
KV cache0.19 GB
Total36.0 GB
Usable48.0 GB
Qwen3.8 35B A3B Distill details · AMD Ryzen AI Max+ 395 page · How this estimate is made
Run commands
llama.cpp
llama-server -hf empero-ai/Qwen3.8-35B-A3B-Distill-GGUF:Q8_0 -c 8192 -ngl 40
Ollama
ollama run qwen3.8
LM Studio
lms get empero-ai/Qwen3.8-35B-A3B-Distill-GGUF # Then load quant Q8_0
Assumptions
- Estimate from memory bandwidth, not a benchmark. Decode speed uses 55–75% of peak bandwidth.
- KV cache is FP16. Engine overhead assumes llama.cpp (0.3 GB + 1% of the weights). Ollama is closer to 0.9 GB + 3%, LM Studio closer to 1 GB + 3%.
- Q8_0 size is the real GGUF file size from Hugging Face.
- Unified memory uses 75% for the GPU by default, and always leaves about 5 GB for the OS.
- Speed is quoted at 8K context, not at the maximum context that still fits.
Larger models that also fit
- Can I run Cyber Tiel Coder 35B A3B GGUF MTP on AMD Ryzen AI Max+ 395? — Runs, Q8_0, 9.1–12 tok/s (estimate)
- Qwen3.5 122B A10B MTP — Tight fit, UD-IQ3_XXS, 7.2–9.8 tok/s (estimate)
- Qwen3 Next 80B A3B Instruct — Tight fit, UD-Q4_K_XL, 7.2–9.8 tok/s (estimate)
Updated 2026-10-24. Profile on this page is the device default.