DeepHermes 3 Llama 3 8B Preview needs about 12.9 GB of memory at Q4_K_M (a 10.0 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 24 quants, from 3.8 GB (IQ1_S) to 13.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 9.5 GB.
DeepHermes 3 Llama 3 8B Preview – 16.5B parameter Llama model
DeepHermes 3 Llama 3 8B Preview is a 16.5B parameter Llama model trained on 131072 context tokens. It supports reasoning and tool usage. The model is available in multiple GGUF quantizations.
Good at
- Reasoning
- Tool usage
- Large context handling
Limits
- No vision support
- License not specified
- Requires high VRAM for larger quants
Best for
- Chatbot development
- Tool integration
- Complex reasoning tasks
Who it’s for. Developers building conversational agents that need reasoning and tool use. Researchers exploring large Llama models with GGUF quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 3.8 GB | 6.7 GB | Fits | Get file → | |
| IQ1_M | 4.1 GB | 7.0 GB | Fits | Get file → | |
| IQ2_XXS | 4.7 GB | 7.5 GB | Tight | Get file → | |
| IQ2_XS | 5.1 GB | 8.0 GB | Too big | Get file → | |
| IQ2_S | 5.4 GB | 8.3 GB | Too big | Get file → | |
| IQ2_M | 5.8 GB | 8.7 GB | Too big | Get file → | |
| Q2_K_S | 5.9 GB | 8.8 GB | Too big | Get file → | |
| Q2_K | 6.3 GB | 9.2 GB | Too big | Get file → | |
| IQ3_XXS | 6.5 GB | 9.4 GB | Too big | Get file → | |
| IQ3_XS | 7.0 GB | 9.9 GB | Too big | Get file → | |
| Q3_K_S | 7.3 GB | 10.2 GB | Too big | Get file → | |
| IQ3_S | 7.4 GB | 10.2 GB | Too big | Get file → | |
| IQ3_M | 7.6 GB | 10.5 GB | Too big | Get file → | |
| Q3_K_M | 8.1 GB | 11.0 GB | Too big | Get file → | |
| Q3_K_L | 8.8 GB | 11.7 GB | Too big | Get file → | |
| IQ4_XS | 9.0 GB | 11.9 GB | Too big | Get file → | |
| Q4_0 | 9.5 GB | 12.4 GB | Too big | Get file → | |
| IQ4_NL | 9.5 GB | 12.4 GB | Too big | Get file → | |
| Q4_K_S | 9.5 GB | 12.4 GB | Too big | Get file → | |
| Q4_K_M | 10.0 GB | 12.9 GB | Too big | Get file → | |
| Q4_1 | 10.4 GB | 13.3 GB | Too big | Get file → | |
| Q5_K_S | 11.4 GB | 14.3 GB | Too big | Get file → | |
| Q5_K_M | 11.7 GB | 14.6 GB | Too big | Get file → | |
| Q6_K | 13.6 GB | 16.5 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (6.7 GB) or IQ1_M (7 GB). For 12 GB VRAM, Q4_K_M (12.9 GB) is suitable. For 16 GB VRAM, Q5_K_M (14.6 GB) or Q6_K (16.5 GB) can be used. Estimates are approximate.
What GPU do you need for DeepHermes 3 Llama 3 8B Preview?
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: the best quant that fits is IQ2_XS (5.1 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is IQ4_XS (9.0 GB file, about 11.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q5_K_M (11.7 GB file, about 14.6 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (13.6 GB file, about 16.5 GB in use).
Which DeepHermes 3 Llama 3 8B Preview quant should you choose?
Q4_K_M is the usual starting point for DeepHermes 3 Llama 3 8B Preview: it balances file size and quality well. Here it is a 10.0 GB file.
If memory is tight, the smallest file is IQ1_S at 3.8 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 DeepHermes 3 Llama 3 8B Preview
How much VRAM does DeepHermes 3 Llama 3 8B Preview need?
About 12.9 GB at Q4_K_M with an 8K context window. That is the 10.0 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 DeepHermes 3 Llama 3 8B Preview on an 8 GB GPU?
Yes, with IQ2_XS: the 5.1 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of DeepHermes 3 Llama 3 8B Preview GGUF?
It depends on the quant: IQ1_S is 3.8 GB, IQ1_M is 4.1 GB, IQ2_XXS is 4.7 GB, IQ2_XS is 5.1 GB, IQ2_S is 5.4 GB, IQ2_M is 5.8 GB and 18 more.
What context length does DeepHermes 3 Llama 3 8B Preview support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.4 GB at 8K and 9.5 GB at 32K.
Where can I download DeepHermes 3 Llama 3 8B Preview GGUF?
The files are on Hugging Face in the mradermacher/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm-i1-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 DeepHermes 3 Llama 3 8B Preview on 8 GB VRAM?
Yes, use IQ1_S or IQ1_M quantizations, which estimate 6.7 GB or 7 GB memory at 8k context.
Does this model support vision?
No, the model does not support vision.
What is the maximum context length?
The model was trained on 131072 context tokens.