Hermes 3 Llama 3.1 70B needs about 35.1 GB of memory at IQ3_M (a 31.9 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 25 quants, from 15.3 GB (IQ1_S) to 141.1 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
Hermes 3 Llama 3.1 70B – a large generalist LLM with advanced roleplay and function calling
Hermes 3 is a 70.6 billion‑parameter Llama‑3.1 model. It supports ChatML prompts, roleplay, and tools. The model is trained on 131 072 context tokens and licensed under llama3.
Good at
- Roleplay with system prompts
- Structured function calling
- Long‑context conversation
Limits
- No vision support
- Requires large VRAM for full precision
- License limits commercial use
Best for
- Chatbot assistants
- Code generation tasks
- Multi‑turn dialogue systems
Who it’s for. Developers building advanced conversational agents who need robust roleplay and function‑calling capabilities. The model is suitable for research and production use where a large context window is required.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 15.3 GB | 18.5 GB | Too big | Get file → | |
| IQ1_M | 16.8 GB | 19.9 GB | Too big | Get file → | |
| IQ2_XXS | 19.1 GB | 22.3 GB | Too big | Get file → | |
| IQ2_XS | 21.1 GB | 24.3 GB | Too big | Get file → | |
| IQ2_S | 22.2 GB | 25.4 GB | Too big | Get file → | |
| IQ2_M | 24.1 GB | 27.3 GB | Too big | Get file → | |
| Q2_K_S | 24.5 GB | 27.7 GB | Too big | Get file → | |
| Q2_K | 26.4 GB | 29.6 GB | Too big | Get file → | |
| IQ3_XXS | 27.5 GB | 30.7 GB | Too big | Get file → | |
| IQ3_XS | 29.3 GB | 32.5 GB | Too big | Get file → | |
| IQ3_S | 30.9 GB | 34.1 GB | Too big | Get file → | |
| Q3_K_S | 30.9 GB | 34.1 GB | Too big | Get file → | |
| IQ3_M | 31.9 GB | 35.1 GB | Too big | Get file → | |
| Q3_K | 34.3 GB | 37.5 GB | Too big | Get file → | |
| Q3_K_L | 37.1 GB | 40.3 GB | Too big | Get file → | |
| IQ4_XS | 37.9 GB | 41.1 GB | Too big | Get file → | |
| IQ4_NL | 40.1 GB | 43.2 GB | Too big | Get file → | |
| Q4_K_S | 40.3 GB | 43.5 GB | Too big | Get file → | |
| Q4_K | 42.5 GB | 45.7 GB | Too big | Get file → | |
| Q5_K_S | 48.7 GB (3 parts) | 51.8 GB | Too big | Get file → | |
| Q5_K | 49.9 GB (3 parts) | 53.1 GB | Too big | Get file → | |
| Q6_K | 57.9 GB (3 parts) | 61.1 GB | Too big | Get file → | |
| Q8_0 | 75.0 GB (4 parts) | 78.2 GB | Too big | Get file → | |
| BF16 | 141.1 GB (6 parts) | 144.3 GB | Too big | Get file → | |
| — | 141.1 GB (6 parts) | 144.3 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (15.34 GB file, 18.5 GB memory at 8 k context). For 12 GB VRAM, IQ2_XS (21.14 GB file, 24.3 GB memory). For 24 GB VRAM, Q4_K (42.52 GB file, 45.7 GB memory). Split files can be merged with gguf‑split.
What GPU do you need for Hermes 3 Llama 3.1 70B?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is IQ2_XXS (19.1 GB file, about 22.3 GB in use).
- 32 GB VRAM: the best quant that fits is IQ3_XXS (27.5 GB file, about 30.7 GB in use).
- 48 GB VRAM: the best quant that fits is Q4_K (42.5 GB file, about 45.7 GB in use).
Which Hermes 3 Llama 3.1 70B quant should you choose?
IQ3_M (31.9 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is IQ1_S at 15.3 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Hermes 3 Llama 3.1 70B
How much VRAM does Hermes 3 Llama 3.1 70B need?
About 35.1 GB at IQ3_M with an 8K context window. That is the 31.9 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Hermes 3 Llama 3.1 70B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 18.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Hermes 3 Llama 3.1 70B GGUF?
It depends on the quant: IQ1_S is 15.3 GB, IQ1_M is 16.8 GB, IQ2_XXS is 19.1 GB, IQ2_XS is 21.1 GB, IQ2_S is 22.2 GB, IQ2_M is 24.1 GB and 19 more.
What context length does Hermes 3 Llama 3.1 70B support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.
Where can I download Hermes 3 Llama 3.1 70B GGUF?
The files are on Hugging Face in the legraphista/Hermes-3-Llama-3.1-70B-IMat-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Hermes 3 Llama 3.1 70B use?
Hugging Face lists the license as llama3. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Hermes 3 on 8 GB VRAM?
Use the IQ1_S quantization; it requires about 18.5 GB memory at 8 k context, so 8 GB VRAM is insufficient for full inference.
Does Hermes 3 support vision?
No, the model has no vision capabilities.
What prompt format does Hermes 3 use?
Hermes 3 uses ChatML, the same format as OpenAI’s ChatGPT API.