Can I run it?
Can I run deepseek v4.1 flash on AMD Ryzen AI Max+ 395?
Won't fit
Won't fit on AMD Ryzen AI Max+ 395. The smallest quant Q2_K is 294.3 GB before KV cache, and usable memory is 48.0 GB.
Best quantQ2_K est.
Working context—
Max that fits—
Speed—Estimate from memory bandwidth, not a benchmark. Method.
Weights294.3 GB
KV cache0.00 GB
Total0.00 GB
Usable48.0 GB
deepseek v4.1 flash details · AMD Ryzen AI Max+ 395 page · How this estimate is made
Run commands
llama.cpp
# Quant size is estimated — the file may not be published yet llama-server -hf antirez/deepseek-v4.1-flash-gguf:Q2_K -c 2048 -ngl 0
Ollama
ollama run deepseek-v4.1-flash
LM Studio
# Quant size is estimated — the file may not be published yet lms get antirez/deepseek-v4.1-flash-gguf # Then load quant Q2_K
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%.
- No display reserve on this device.
- Usable memory for this profile is 48.0 GB.
Models that fit this machine more comfortably
- Mistral Medium 3.5 128B — Tight fit, UD-Q2_K_XL, 2.8–3.9 tok/s (estimate)
- Qwen3.5 122B A10B MTP — Tight fit, UD-IQ3_XXS, 7.2–9.8 tok/s (estimate)
- Mistral Small 4 119B 2603 — Tight fit, UD-IQ3_S, 7.7–11 tok/s (estimate)
Updated 2026-10-24. Profile on this page is the device default.