Can DeepSeek OCR 2 run on the Ryzen AI Max+ 395 128GB?
Yes. At 8K context the best fit is F16, using about 6.6 GB of the 109 GB usable on the Ryzen AI Max+ 395 128GB. Estimated speed ceiling: ~124 tokens/sec.
+ 0.5 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 7.1 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 | Max tok/s (est., 8K) |
|---|---|---|---|
| 2-bit (Q2_K) | 2.1 GB Fits | 2.3 GB Fits | 572 |
| 3-bit (Q3_K_M) | 2.4 GB Fits | 2.7 GB Fits | 439 |
| 4-bit (Q4_K_M) • | 2.7 GB Fits | 2.9 GB Fits | 373 |
| 5-bit (Q5_K_M) | 3.1 GB Fits | 3.4 GB Fits | 301 |
| 6-bit (Q6_K) | 3.5 GB Fits | 3.7 GB Fits | 261 |
| 8-bit (Q8_0) • | 3.8 GB Fits | 4.0 GB Fits | 232 |
| 16-bit (F16/BF16) • | 6.4 GB Fits | 6.6 GB Fits | 124 |
• real GGUF file size from sabafallah/DeepSeek-OCR-2-GGUF. Speed is a bandwidth ceiling (256 GB/s), not a benchmark. Methodology.
What fits instead
- Cheapest listed GPU that runs DeepSeek OCR 2: 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
DeepSeek OCR 2 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 (deepseek-ai/DeepSeek-OCR-2), AMD specs. Model data last checked 2026-11-18; refreshed hourly.