Qwen on AMD Strix Halo
Can I run Qwen2.5 7B on an Ryzen AI Max+ 395 128GB?
Yes. Qwen2.5 7B at Q4_K_M uses 5.3 GB of the 96.0 GB available on a Ryzen AI Max+ 395 128GB, and runs at about 29.1 tokens per second. You can push the context to 128K.
Runs comfortably
5.3 GB of 96.0 GB · 6%096 GB
Weights
4.4 GB
KV cache
0.4 GB
Runtime overhead
0.5 GB
Qwen2.5 7B at Q4_K_M leaves 90.7 GB spare on a Ryzen AI Max+ 395 128GB. There is room to raise the context length or move up a quantisation level.
Generation29.1tok/s
Prompt processing1378tok/s
Max context128Ktokens
KV per 1K tokens0GB
Every quantisation of Qwen2.5 7B on a Ryzen AI Max+ 395 128GB
Highlighted row is the highest quality that still fits at 8K context.
| Quantisation | bpw | Weights | Total | Verdict | Max ctx | tok/s |
|---|---|---|---|---|---|---|
| FP16 / BF16 | 16.00 | 14.2 GB | 15.1 GB | Runs comfortably | 128K | 9.32 |
| INT8 / W8A8 | 8.50 | 7.3 GB | 8.2 GB | Runs comfortably | 128K | 17.8 |
| Q8_0 (GGUF) | 8.50 | 7.3 GB | 8.2 GB | Runs comfortably | 128K | 17.8 |
| FP8 (E4M3) | 8.00 | 7.1 GB | 8.0 GB | Runs comfortably | 128K | 18.3 |
| Q6_K | 6.56 | 5.8 GB | 6.8 GB | Runs comfortably | 128K | 22.2 |
| AWQ 4-bit | 4.25 | 5.3 GB | 6.2 GB | Runs comfortably | 128K | 24.4 |
| GPTQ 4-bit | 4.25 | 5.3 GB | 6.2 GB | Runs comfortably | 128K | 24.4 |
| MXFP4 | 4.25 | 5.3 GB | 6.2 GB | Runs comfortably | 128K | 24.4 |
| Q5_K_M | 5.67 | 5.0 GB | 6.0 GB | Runs comfortably | 128K | 25.5 |
| Q5_K_S | 5.52 | 4.9 GB | 5.8 GB | Runs comfortably | 128K | 26.2 |
| Q4_K_M | 4.85 | 4.4 GB | 5.3 GB | Runs comfortably | 128K | 29.1 |
| Q4_K_S | 4.58 | 4.2 GB | 5.1 GB | Runs comfortably | 128K | 30.4 |
| Q4_0 | 4.55 | 4.2 GB | 5.1 GB | Runs comfortably | 128K | 30.6 |
| IQ4_XS | 4.25 | 3.9 GB | 4.9 GB | Runs comfortably | 128K | 32.2 |
| Q3_K_M | 3.91 | 3.7 GB | 4.6 GB | Runs comfortably | 128K | 34.4 |
| IQ3_M | 3.70 | 3.5 GB | 4.5 GB | Runs comfortably | 128K | 35.8 |
| IQ3_XXS | 3.06 | 3.0 GB | 4.0 GB | Runs comfortably | 128K | 41.2 |
| Q2_K | 2.63 | 2.7 GB | 3.6 GB | Runs comfortably | 128K | 45.8 |
| IQ2_XXS | 2.06 | 2.3 GB | 3.2 GB | Runs comfortably | 128K | 53.7 |
| IQ1_M | 1.75 | 2.0 GB | 3.0 GB | Runs comfortably | 128K | 59.2 |