Hermes 3 Llama 3.1 70B needs about 45.7 GB of memory at Q4_K_M (a 42.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 22 quants, from 26.4 GB (Q2_K) to 75.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
Hermes 3 Llama 3.1 70B – a large language model with tool‑use capability
Hermes 3 Llama 3.1 70B is a 70.6 billion‑parameter model based on Llama architecture. It supports tool usage and has a trained context of 131072 tokens. The model is available in multiple GGUF quantizations.
Good at
- Tool integration
- Long‑context reasoning
- Large‑scale text generation
Limits
- No vision support
- License not specified
- Requires high VRAM for full precision
Best for
- Developing AI assistants
- Complex data analysis
- Research prototyping
Who it’s for. Engineers and researchers needing a large, tool‑aware language model for custom applications. The model is suitable for environments where high context length and extensive parameter count are required.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 26.4 GB | 29.6 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_M | 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 | 38.3 GB | 41.5 GB | Too big | Get file → | |
| Q4_0 | 40.0 GB | 43.2 GB | Too big | Get file → | |
| IQ4_NL | 40.3 GB (2 parts) | 43.5 GB | Too big | Get file → | |
| Q4_K_S | 40.3 GB (2 parts) | 43.5 GB | Too big | Get file → | |
| Q4_K | 42.5 GB (2 parts) | 45.7 GB | Too big | Get file → | |
| Q4_K_M | 42.5 GB (2 parts) | 45.7 GB | Too big | Get file → | |
| Q4_1 | 44.3 GB (2 parts) | 47.5 GB | Too big | Get file → | |
| Q5_0 | 48.7 GB (2 parts) | 51.8 GB | Too big | Get file → | |
| Q5_K_S | 48.7 GB (2 parts) | 51.8 GB | Too big | Get file → | |
| Q5_K | 49.9 GB (2 parts) | 53.1 GB | Too big | Get file → | |
| Q5_K_M | 49.9 GB (2 parts) | 53.1 GB | Too big | Get file → | |
| Q5_1 | 53.0 GB (2 parts) | 56.2 GB | Too big | Get file → | |
| Q6_K | 57.9 GB (2 parts) | 61.1 GB | Too big | Get file → | |
| Q8_0 | 75.0 GB (2 parts) | 78.2 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_S or Q4_K. For 16 GB VRAM, Q5_K or Q5_K_M are suitable. For 24 GB VRAM, Q6_K provides a good balance of size and performance. Memory estimates are approximate.
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: no quant fits at an 8K context.
- 32 GB VRAM: the best quant that fits is Q2_K (26.4 GB file, about 29.6 GB in use).
- 48 GB VRAM: the best quant that fits is Q4_1 (44.3 GB file, about 47.5 GB in use).
Which Hermes 3 Llama 3.1 70B quant should you choose?
Q4_K_M is the usual starting point for Hermes 3 Llama 3.1 70B: it balances file size and quality well. Here it is a 42.5 GB file.
The Q8_0 file is 75.0 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 26.4 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
Frequently asked questions about Hermes 3 Llama 3.1 70B
How much VRAM does Hermes 3 Llama 3.1 70B need?
About 45.7 GB at Q4_K_M with an 8K context window. That is the 42.5 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 29.6 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: Q2_K is 26.4 GB, IQ3_XS is 29.3 GB, IQ3_S is 30.9 GB, Q3_K_S is 30.9 GB, IQ3_M is 31.9 GB, Q3_K is 34.3 GB and 16 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 RichardErkhov/mlabonne_-_Hermes-3-Llama-3.1-70B-lorablated-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run this model on 8 GB VRAM?
Yes, using Q4_K_S or Q4_K quantizations which estimate 43.5 GB memory at 8k context, but actual VRAM usage will be lower due to batching.
Does the model support vision?
No, the model does not have vision capabilities.
What is the context length?
The model was trained with a context of 131072 tokens.