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
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) | 2.8 GB Fits | 3.4 GB Fits | 6.7 GB Fits | 20.2 GB Fits | 154 |
| 3-bit (Q3_K_M) | 3.3 GB Fits | 3.8 GB Fits | 7.2 GB Fits | 20.7 GB Fits | 118 |
| 4-bit (Q4_K_M) • | 3.6 GB Fits | 4.1 GB Fits | 7.5 GB Fits | 21.0 GB Fits | 103 |
| 5-bit (Q5_K_M) | 4.2 GB Fits | 4.8 GB Fits | 8.1 GB Fits | 21.6 GB Fits | 81 |
| 6-bit (Q6_K) | 4.6 GB Fits | 5.2 GB Fits | 8.6 GB Fits | 22.1 GB Fits | 70 |
| 8-bit (Q8_0) • | 5.2 GB Fits | 5.8 GB Fits | 9.2 GB Fits | 22.7 GB Fits | 60 |
| 16-bit (F16/BF16) • | 8.8 GB Fits | 9.3 GB Fits | 12.7 GB Fits | 26.2 GB Fits | 32 |
• 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
- Cheapest listed GPU that runs Qwen3 VL 4B Instruct: Arc B580 (12 GB, launch MSRP $249) at F16, fully in VRAM at 8K context.
- Largest popular model that fits the Ryzen AI Max+ 395 128GB: gpt-oss 120B (117B, MoE) at F16, about 61.9 GB at 8K context.
"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.