Can Nous Hermes 2 Mixtral 8x7B DPO run on the RTX A6000?
Yes. At 8K context the best fit is Q6_K, using about 37.2 GB of the 45.6 GB usable on the RTX A6000. Estimated speed ceiling: ~73 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|
| 2-bit (Q2_K) • | 17.1 GB Fits | 17.6 GB Fits | 20.6 GB Fits | 161 |
| 3-bit (Q3_K_M) • | 22.0 GB Fits | 22.5 GB Fits | 25.5 GB Fits | 124 |
| 4-bit (Q4_K_M) • | 27.5 GB Fits | 28.0 GB Fits | 31.0 GB Fits | 98 |
| 5-bit (Q5_K_M) • | 31.9 GB Fits | 32.4 GB Fits | 35.4 GB Fits | 84 |
| 6-bit (Q6_K) • | 36.7 GB Fits | 37.2 GB Fits | 40.2 GB Fits | 73 |
| 8-bit (Q8_0) • | 47.2 GB No | 47.7 GB No | 50.7 GB No | — |
| 16-bit (F16/BF16) | 88.0 GB No | 88.5 GB No | 91.5 GB No | — |
• real GGUF file size from TheBloke/Nous-Hermes-2-Mixtral-8x7B-DPO-GGUF. Speed is a bandwidth ceiling (768 GB/s), not a benchmark. Methodology.
More
Nous Hermes 2 Mixtral 8x7B DPO on every GPU and Mac · Every model that runs on the RTX A6000 · Other models that fit 48 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO), NVIDIA specs. Data as of 2026-11-17.