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

Can Qwen3 VL 4B Instruct run on the Ryzen AI Max+ 395 128GB?

Yes. At 8K context the best fit is F16, using about 9.3 GB of the 109 GB usable on the Ryzen AI Max+ 395 128GB. Estimated speed ceiling: ~32 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 9.7 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)2.8 GB Fits3.4 GB Fits6.7 GB Fits20.2 GB Fits154
3-bit (Q3_K_M)3.3 GB Fits3.8 GB Fits7.2 GB Fits20.7 GB Fits118
4-bit (Q4_K_M) •3.6 GB Fits4.1 GB Fits7.5 GB Fits21.0 GB Fits103
5-bit (Q5_K_M)4.2 GB Fits4.8 GB Fits8.1 GB Fits21.6 GB Fits81
6-bit (Q6_K)4.6 GB Fits5.2 GB Fits8.6 GB Fits22.1 GB Fits70
8-bit (Q8_0) •5.2 GB Fits5.8 GB Fits9.2 GB Fits22.7 GB Fits60
16-bit (F16/BF16) •8.8 GB Fits9.3 GB Fits12.7 GB Fits26.2 GB Fits32

• real GGUF file size from Qwen/Qwen3-VL-4B-Instruct-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

Qwen3 VL 4B Instruct 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 (Qwen/Qwen3-VL-4B-Instruct), AMD specs. Model data last checked 2026-11-18; refreshed hourly.