Nous Hermes 2 Mixtral 8x7B DPO — Hardware Requirements & GPU Compatibility
Chat
Nous-Hermes-2-Mixtral-8x7B-DPO is Nous Research's instruction-tuned chat model built on top of Mistral AI's Mixtral-8x7B-v0.1 Mixture-of-Experts base, trained through supervised fine-tuning followed by direct preference optimization (DPO) on over a million largely GPT-4-generated examples plus other curated open data. It uses the ChatML prompt format for structured multi-turn dialogue and system prompts, and improved on GPT4All, AGIEval, and BigBench benchmarks over both the base Mixtral model and Mistral's own Mixtral-Instruct. With 8 experts and 2 active per token, roughly 12.9 billion active out of 46.7 billion total, it needs a high-end consumer GPU or multi-GPU setup once quantized. Context length is 32,768 tokens. It is released under the Apache 2.0 license, permitting unrestricted commercial and research use. It was published in January 2024, alongside an SFT-only sibling release for comparison.
13.6K downloads
459 likesSpecifications
- Publisher
- Nous Research
- Family
- Mixtral
- Parameters
- 46.7B
- Architecture
- MixtralForCausalLM
- Context Length
- 32,768 tokens
- Vocabulary Size
- 32,002
- Release Date
- 2024-01-11
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Nous Hermes 2 Mixtral 8x7B DPO Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 20.4 GB | 24.4 GB | 19.85 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 21 GB | 25.0 GB | 20.43 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 23.3 GB | 27.4 GB | 22.77 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 23.9 GB | 27.9 GB | 23.35 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 28.6 GB | 32.6 GB | 28.02 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 33.8 GB | 37.9 GB | 33.28 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 39.1 GB | 43.1 GB | 38.53 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 47.3 GB | 51.3 GB | 46.70 GB | 8-bit quantization, near-lossless |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run Nous Hermes 2 Mixtral 8x7B DPO?
Q4_K_M · 28.6 GBNous Hermes 2 Mixtral 8x7B DPO (Q4_K_M) requires 28.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 38+ GB is recommended. Using the full 33K context window can add up to 4.0 GB, bringing total usage to 32.6 GB. 1 GPU can run it, including NVIDIA GeForce RTX 5090.
All compatible consumer-level GPUs are running near their VRAM limit. You may also want to consider professional GPUs (e.g., NVIDIA A100, H100) which offer significantly more VRAM. For more headroom and better throughput, consider a multi-GPU configuration with tensor parallelism (supported by tools like vLLM, llama.cpp, or text-generation-inference).
Decent
— Enough VRAM, may be tightWhich Devices Can Run Nous Hermes 2 Mixtral 8x7B DPO?
Q4_K_M · 28.6 GB31 devices with unified memory can run Nous Hermes 2 Mixtral 8x7B DPO, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Studio M4 Max (36 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightWhere to Download Nous Hermes 2 Mixtral 8x7B DPO
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Benchmarks
Benchmark details →Related Models
Frequently Asked Questions
- How much VRAM does Nous Hermes 2 Mixtral 8x7B DPO need?
Nous Hermes 2 Mixtral 8x7B DPO requires 28.6 GB of VRAM at Q4_K_M, or 94.0 GB at BF16. Full 33K context adds up to 4.0 GB (32.6 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 46.7B × 4.8 bits ÷ 8 = 28 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 4.6 GB (at full 33K context)
VRAM usage by quantization
Q4_K_M28.6 GBQ4_K_M + full context32.6 GB- Can NVIDIA GeForce RTX 4090 run Nous Hermes 2 Mixtral 8x7B DPO?
Yes, at Q4_0 (23.9 GB) or lower. Higher quantizations like Q3_K_L (24.5 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for Nous Hermes 2 Mixtral 8x7B DPO?
For Nous Hermes 2 Mixtral 8x7B DPO, Q4_K_M (28.6 GB) offers the best balance of quality and VRAM usage. Q5_0 (29.8 GB) provides better quality if you have the VRAM. The smallest option is IQ3_XS at 19.8 GB.
VRAM requirement by quantization
IQ3_XS19.8 GBIQ3_M21.6 GBIQ4_XS25.7 GBQ4_K_M ★28.6 GBQ5_K_S32.7 GBBF1694.0 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Nous Hermes 2 Mixtral 8x7B DPO on a Mac?
Nous Hermes 2 Mixtral 8x7B DPO requires at least 19.8 GB at IQ3_XS, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Nous Hermes 2 Mixtral 8x7B DPO locally?
Yes — Nous Hermes 2 Mixtral 8x7B DPO can run locally on consumer hardware. At Q4_K_M quantization it needs 28.6 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Nous Hermes 2 Mixtral 8x7B DPO?
At Q4_K_M, Nous Hermes 2 Mixtral 8x7B DPO can reach ~124 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 28.6 × 0.65 = ~305 tok/s
Estimated speed at Q4_K_M (28.6 GB)
~305 tok/s~305 tok/s~236 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Nous Hermes 2 Mixtral 8x7B DPO?
At Q4_K_M, the download is about 28.02 GB. The full-precision BF16 version is 93.41 GB. The smallest option (IQ3_XS) is 19.26 GB.
- Which GPUs can run Nous Hermes 2 Mixtral 8x7B DPO?
1 consumer GPU can run Nous Hermes 2 Mixtral 8x7B DPO at Q4_K_M (28.6 GB). Top options include NVIDIA GeForce RTX 5090.
- Which devices can run Nous Hermes 2 Mixtral 8x7B DPO?
35 devices with unified memory can run Nous Hermes 2 Mixtral 8x7B DPO at Q4_K_M (28.6 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.