What GPU do I need to run NousResearch/Nous-Hermes-2-Mistral-7B-DPO?
7.2B parameters, published in BF16. View on Hugging Face Full specs & deploy guide
Set up Nous-Hermes-2-Mistral-7B-DPONous-Hermes-2-Mistral-7B-DPO is published by NousResearch on Hugging Face, with 1,478 downloads and 221 likes to date. It's a MistralForCausalLM model built for text-generation, published natively in BF16.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for KV-cache, activations, and fragmentation. Full formula and assumptions: methodology.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 13.5 GB | 16.2 GB | RTX 3090 | 1 | $0.147/hr |
| FP8 (quantized) | 6.7 GB | 8.1 GB | RTX 4070 Super | 1 | $0.110/hr |
| INT4 (quantized) | 3.4 GB | 4.0 GB | RTX 4070 Super | 1 | $0.110/hr |
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run Nous-Hermes-2-Mistral-7B-DPO at its published (BF16) precision: 1× RTX 3090, at $0.147/hr per GPU ($0.147/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Nous-Hermes-2-Mistral-7B-DPO: common questions
Does Nous-Hermes-2-Mistral-7B-DPO fit on a 24 GB GPU?
Yes. At BF16 it needs 16.2 GB of VRAM, so a 24 GB card holds it with 7.8 GB to spare. A 16 GB card is not enough for it at BF16.
What is the least VRAM Nous-Hermes-2-Mistral-7B-DPO can run in?
4.0 GB, at INT4 (quantized), which fits a 6 GB card, against 16.2 GB at BF16. That row assumes an INT4 checkpoint has actually been published for this model, so check its Hugging Face page before planning around it.
Does quantizing Nous-Hermes-2-Mistral-7B-DPO lower the GPU bill?
Yes. At BF16 the cheapest live fit is one RTX 3090 at $0.147/hr. At FP8 (quantized) it drops to one RTX 4070 Super at $0.110/hr, provided a quantized checkpoint exists for it.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More NousResearch models
- Hermes-3-Llama-3.1-8B (8.0B, BF16)
- Meta-Llama-3.1-8B-Instruct (8.0B, BF16)
- Llama-2-7b-hf (6.7B, F16)
- Meta-Llama-3-8B-Instruct (8.0B, BF16)
- Meta-Llama-3-8B (8.0B, BF16)
- Llama-3.2-1B (1.2B, BF16)
