Can I run Nous Hermes 2 Mixtral 8x7B DPO locally?
Nous Hermes 2 Mixtral 8x7B DPO by NousResearch has 47B parameters (13B active per token, 8 experts, 2 used per token). At 4-bit with an 8K context it needs about 28.0 GB of GPU memory. It fits on 33 of 65 GPUs and Macs we track. See all models that fit in 32 GB of VRAM.
Memory needed by quant and context length
GB of GPU memory = weights + KV cache (FP16) + runtime overhead. Weights use real file sizes from TheBloke/Nous-Hermes-2-Mixtral-8x7B-DPO-GGUF where available (marked •), otherwise parameter count × bits per weight. How we calculate.
| Quant | Quality | 4K ctx | 8K ctx | 32K ctx |
|---|---|---|---|---|
| 2-bit (Q2_K) • | rough | 17.1 GB | 17.6 GB | 20.6 GB |
| 3-bit (Q3_K_M) • | usable | 22.0 GB | 22.5 GB | 25.5 GB |
| 4-bit (Q4_K_M) • | good, most popular | 27.5 GB | 28.0 GB | 31.0 GB |
| 5-bit (Q5_K_M) • | very good | 31.9 GB | 32.4 GB | 35.4 GB |
| 6-bit (Q6_K) • | near lossless | 36.7 GB | 37.2 GB | 40.2 GB |
| 8-bit (Q8_0) • | effectively lossless | 47.2 GB | 47.7 GB | 50.7 GB |
| 16-bit (F16/BF16) | original weights | 88.0 GB | 88.5 GB | 91.5 GB |
Which GPUs and Macs run Nous Hermes 2 Mixtral 8x7B DPO?
Best quality quant that fits at 8K context. "Tight" = within 10% of usable memory. Speed is a ceiling from memory bandwidth (real speed is typically 50–80% of it).
Questions
How much VRAM does Nous Hermes 2 Mixtral 8x7B DPO need?
About 28.0 GB at 4-bit (Q4_K_M) with an 8K context: 26.5 GB of weights (real GGUF file size), 1.0 GB of KV cache and 0.5 GB of runtime overhead. At 8-bit it needs about 47.7 GB.
What is the smallest GPU that runs Nous Hermes 2 Mixtral 8x7B DPO?
No single consumer GPU in our table fits it at Q4_K_M with 8K context; the smallest option that does is the A100 40GB (40 GB).
Can I run Nous Hermes 2 Mixtral 8x7B DPO on a Mac?
Yes. At Q4_K_M with 8K context it fits on a Mac M4 Pro 48GB or larger, using the default macOS GPU memory limit.
Similar models
Same family or a similar parameter count, with the VRAM each needs at Q4_K_M and 8K context.
Hermes 4.3 36B
36B · 23.0 GB at 4-bitNous Hermes 2 Yi 34B
34B · 22.1 GB at 4-bitArete 27B
27B · 17.4 GB at 4-bitKimi Linear 48B A3B Instruct
49B · 28.9 GB at 4-bitfalcon 40b
42B · 25.2 GB at 4-bitflint
40B · 23.6 GB at 4-bitModel facts
| Hugging Face repo | NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO |
| Parameters | 46,702,809,088 (47B) · ~13B active (computed from config) |
| Layers / hidden size | 32 / 4096 |
| Attention | GQA; 32 heads, 8 KV heads, head dim 128 |
| KV cache per token (FP16) | 128.0 KiB |
| Max context | 32,768 tokens |
| License | apache-2.0 |
| Released on HF | Jan 11, 2024 |
| Downloads (30d) / likes | 14,273 / 461 |
Sources: Hugging Face model API · config.json (NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.