Hermes-2-Theta-Llama-3-70B-32k 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 12 quants, from 26.4 GB (Q2_K) to 49.9 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
Hermes‑2‑Theta‑Llama‑3‑70B‑32k – a 70.6B Llama‑3 model with tool‑calling and structured output support
Hermes‑2‑Theta‑Llama‑3‑70B‑32k is a 70.6B parameter Llama‑3 model trained with 32k context tokens. It is merged and further RLHF’ed from Hermes‑2 Pro and Llama‑3 Instruct. The model supports function calling, JSON structured outputs, and feature extraction from RAG documents.
Good at
- Function calling and tool use
- Structured JSON output
- Long‑context 32k token handling
Limits
- No vision support
- Requires large VRAM for full precision
- License is llama3
Best for
- Chatbots needing tool integration
- Data extraction from documents
- Long‑form dialogue with 32k context
Who it’s for. Developers building chat interfaces that require structured outputs and function calling. Researchers needing a large Llama‑3 variant with extended context for RAG tasks.
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_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_K_S | 40.3 GB | 43.5 GB | Too big | Get file → | |
| Q4_K_M | 42.5 GB | 45.7 GB | Too big | Get file → | |
| Q5_K_S | 48.7 GB | 51.8 GB | Too big | Get file → | |
| Q5_K_M | 49.9 GB | 53.1 GB | Too big | Get file → |
For 8 GB VRAM use Q2_K (26.38 GB file, ~29.6 GB memory at 8k context). For 16 GB VRAM use Q4_K_M (42.52 GB file, ~45.7 GB memory). For 24 GB VRAM use Q5_K_M (49.95 GB file, ~53.1 GB memory). Estimates are approximate.
What GPU do you need for Hermes-2-Theta-Llama-3-70B-32k?
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_K_M (42.5 GB file, about 45.7 GB in use).
Which Hermes-2-Theta-Llama-3-70B-32k quant should you choose?
Q4_K_M is the usual starting point for Hermes-2-Theta-Llama-3-70B-32k: it balances file size and quality well. Here it is a 42.5 GB file.
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
Source
Frequently asked questions about Hermes-2-Theta-Llama-3-70B-32k
How much VRAM does Hermes-2-Theta-Llama-3-70B-32k 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-2-Theta-Llama-3-70B-32k 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-2-Theta-Llama-3-70B-32k 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_M is 34.3 GB and 6 more.
What context length does Hermes-2-Theta-Llama-3-70B-32k support?
The GGUF header lists a trained context length of 32,768 tokens (32K). 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-2-Theta-Llama-3-70B-32k GGUF?
The files are on Hugging Face in the mradermacher/Hermes-2-Theta-Llama-3-70B-32k-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-2-Theta-Llama-3-70B-32k 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‑2‑Theta‑Llama‑3‑70B‑32k on 8 GB VRAM?
Use the Q2_K quant; it requires about 29.6 GB memory at 8k context, which is above 8 GB, so it will not fit. A smaller quant is needed.
Does this model support vision tasks?
No, the model has no vision capability.
What license applies to this model?
The model is licensed under llama3.