GPUs & Macs › AMD Radeon RX 6950 XT
AMD Radeon RX 6950 XT: local LLM speed
2 measured results for the AMD Radeon RX 6950 XT.
Measured results
| Model | Generate tok/s | Prompt tok/s | Quant | Backend | Test | Source |
|---|---|---|---|---|---|---|
| Llama 3.1 8B Instruct | 6.1 | 1,024 | Q4_K_M | llamafile | LocalScore avg | LocalScore details |
| Qwen2.5 14B Instruct | 3.3 | 549 | Q4_K_M | llamafile | LocalScore avg | LocalScore details |
What fits on the AMD Radeon RX 6950 XT
Estimates for this chip are scaled from a measured run: Llama 3.1 8B Instruct Q4_K_M at 6.1 tok/s (llamafile, source). Fit assumes the whole model in GPU memory with ~8K context.
| Model | Best quant that fits | File | Expected tok/s |
|---|---|---|---|
| Qwen3.8-27B | UD-IQ3_XXS | 10.9 GB | 2.8 estimate |
| gemma-4-12B-it | Q8_0 | 12.7 GB | 2.4 estimate |
| Qwen3.5-9B | Q8_0 | 9.5 GB | 3.2 estimate |
| Qwen3.5-4B | Q8_0 | 4.5 GB | 6.7 estimate |
| Qwen3.6-35B-A3B | UD-IQ3_XXS | 13.2 GB | 13.3 estimate |
| gemma-4-26B-A4B-it | UD-IQ4_XS | 13.6 GB | 7.2 estimate |
| MiMo-V2.6-Distill-Qwen-9B | Q8_0 | 9.5 GB | 3.2 estimate |
| gemma-4-E4B-it | Q8_0 | 8.2 GB | 3.7 estimate |
| Muse-Glimmer-30B | UD-IQ3_XXS | 13.1 GB | 2.3 estimate |
| Qwen3-4B | Q8_0 | 4.3 GB | 7.1 estimate |
| gemma-4-31B-it | UD-IQ3_XXS | 11.8 GB | 2.6 estimate |
| gemma-4-12B-it-qat-q4_0-unquantized | UD-Q4_K_XL | 6.7 GB | 4.5 estimate |
| gemma-3-1b-it | Q8_0 | 1.1 GB | 25.2 estimate |
| gemma-4-E2B-it | Q8_0 | 5.0 GB | 6.1 estimate |
Similar hardware
AMD Radeon RX 9070 XT · AMD Radeon RX 9070 · AMD Radeon RX 7800 XT · AMD Radeon RX 7900 GRE · AMD Radeon RX 6900 XT · AMD Radeon RX 6800 · AMD Radeon VII · AMD Radeon RX 6800 XT