RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?OllamaStart hereAPI pricesVRAM calculatorNew

Can Maxwell V1 Flash run on the Ryzen AI Max+ 395 128GB?

Yes. At 8K context the best fit is F16, using about 68.2 GB of the 109 GB usable on the Ryzen AI Max+ 395 128GB. Estimated speed ceiling: ~58 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K)13.8 GB Fits14.0 GB Fits15.0 GB Fits19.3 GB Fits301
3-bit (Q3_K_M)17.7 GB Fits17.9 GB Fits18.9 GB Fits23.2 GB Fits231
4-bit (Q4_K_M)21.9 GB Fits22.1 GB Fits23.1 GB Fits27.4 GB Fits184
5-bit (Q5_K_M)25.4 GB Fits25.6 GB Fits26.6 GB Fits30.8 GB Fits158
6-bit (Q6_K)29.1 GB Fits29.2 GB Fits30.3 GB Fits34.5 GB Fits138
8-bit (Q8_0) •36.7 GB Fits36.9 GB Fits38.0 GB Fits42.2 GB Fits108
16-bit (F16/BF16) •68.0 GB Fits68.2 GB Fits69.3 GB Fits73.5 GB Fits58

• real GGUF file size from AtomicChat/Maxwell-V1-Flash-GGUF. Speed is a bandwidth ceiling (256 GB/s), not a benchmark. Methodology.

What fits instead

"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.

More

Maxwell V1 Flash on every GPU and Mac · Every model that runs on the Ryzen AI Max+ 395 128GB · Other models that fit 64 GB VRAM · Try other settings in the calculator

Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs

Data: Hugging Face Hub (maxwell-model/Maxwell-V1-Flash), AMD specs. Model data last checked 2026-11-18; refreshed hourly.