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

Can WeVisOne VL 2B run on the Ryzen AI Max+ 395 128GB?

Yes. At 8K context the best fit is F16, using about 5.4 GB of the 109 GB usable on the Ryzen AI Max+ 395 128GB. Estimated speed ceiling: ~63 tokens/sec.

+ 0.4 GB with image input. The figures on this page are for text only. With image input enabled, the vision projector (mmproj) file loads alongside the model: F16 at 8K context then needs about 5.8 GB (still fits). llama.cpp's -hf downloads and loads it automatically unless you add --no-mmproj. Calculator with image input on.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •1.9 GB Fits2.4 GB Fits5.0 GB Fits15.5 GB Fits290
3-bit (Q3_K_M) •2.1 GB Fits2.6 GB Fits5.2 GB Fits15.7 GB Fits238
4-bit (Q4_K_M) •2.3 GB Fits2.8 GB Fits5.4 GB Fits15.9 GB Fits199
5-bit (Q5_K_M) •2.5 GB Fits2.9 GB Fits5.6 GB Fits16.1 GB Fits174
6-bit (Q6_K) •2.7 GB Fits3.1 GB Fits5.8 GB Fits16.3 GB Fits153
8-bit (Q8_0) •3.1 GB Fits3.6 GB Fits6.2 GB Fits16.7 GB Fits118
16-bit (F16/BF16) •4.9 GB Fits5.4 GB Fits8.0 GB Fits18.5 GB Fits63

• real GGUF file size from mradermacher/WeVisOne-VL-2B-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

WeVisOne VL 2B 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 (tencent/WeVisOne-VL-2B), AMD specs. Model data last checked 2026-11-18; refreshed hourly.