Can gpt-oss 120B run on the Ryzen AI Max+ 395 128GB?
Yes. At 8K context the best fit is F16, using about 61.9 GB of the 109 GB usable on the Ryzen AI Max+ 395 128GB. Estimated speed ceiling: ~80 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) • | 59.3 GB Fits | 59.5 GB Fits | 60.3 GB Fits | 63.7 GB Fits | 83 |
| 3-bit (Q3_K_M) • | 59.3 GB Fits | 59.5 GB Fits | 60.3 GB Fits | 63.7 GB Fits | 83 |
| 4-bit (Q4_K_M) • | 59.5 GB Fits | 59.6 GB Fits | 60.4 GB Fits | 63.8 GB Fits | 83 |
| 5-bit (Q5_K_M) | 78.5 GB Fits | 78.6 GB Fits | 79.4 GB Fits | 82.8 GB Fits | 62 |
| 6-bit (Q6_K) • | 59.9 GB Fits | 60.0 GB Fits | 60.9 GB Fits | 64.2 GB Fits | 82 |
| 8-bit (Q8_0) • | 60.0 GB Fits | 60.1 GB Fits | 60.9 GB Fits | 64.3 GB Fits | 82 |
| 16-bit (F16/BF16) • | 61.8 GB Fits | 61.9 GB Fits | 62.8 GB Fits | 66.2 GB Fits | 80 |
• real GGUF file size from bartowski/openai_gpt-oss-120b-GGUF. Speed is a bandwidth ceiling (256 GB/s), not a benchmark. Methodology.
What fits instead
- Cheapest listed GPU that runs gpt-oss 120B: 2x RTX 5090 (2× 32 GB, launch MSRP $3,998) at Q8_0, fully in VRAM at 8K context.
- Largest popular model that fits the Ryzen AI Max+ 395 128GB: GLM 4.5 Air (110B, MoE) at Q6_K, about 94.5 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
gpt-oss 120B 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 (openai/gpt-oss-120b), AMD specs. Model data last checked 2026-11-18; refreshed hourly.