Can I run it?
Can I run Qwen3.8 Flash Next on Apple M4 Max (40-core GPU)?
Won't fit
Won't fit on Apple M4 Max (40-core GPU). The smallest quant UD-IQ1_S is 67.6 GB before KV cache, and usable memory is 36.0 GB.
Best quantUD-IQ1_S
Working context—
Max that fits—
Speed—Estimate from memory bandwidth, not a benchmark. Method.
Weights67.6 GB
KV cache0.00 GB
Total0.00 GB
Usable36.0 GB
Qwen3.8 Flash Next details · Apple M4 Max (40-core GPU) page · How this estimate is made
Run commands
llama.cpp
llama-server -hf unsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ1_S -c 2048 -ngl 0
Ollama
ollama run qwen3.8-flash-next
LM Studio
lms get unsloth/Qwen3.8-Flash-Next-GGUF # Then load quant UD-IQ1_S
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 36.0 GB.
Models that fit this machine more comfortably
- Mistral Medium 3.5 128B — Heavily degraded, UD-IQ2_XXS, 8.2–11 tok/s (estimate)
- Mistral Small 4 119B 2603 — Heavily degraded, UD-IQ2_XXS, 21–28 tok/s (estimate)
- Llama 4 Scout 17B 16E Instruct — Heavily degraded, UD-IQ1_M, 19–26 tok/s (estimate)
Updated 2026-10-24. Profile on this page is the device default.