LL

Hermes 3 Llama 3.1 70B

LlamaGGUF by mradermacherUpdated 2024-08-17
Download on Hugging Face
Parameters70.6B
Context128K
Layers80
Architecturellama
Smallest quant26.4 GB
Quick answer

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 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 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 3.1. It supports tool usage and was created by merging a censored Hermes‑3 model with an abliterated LoRA adapter. The model is available in multiple GGUF quantizations.

Good at

  • Tool‑based reasoning
  • Large context handling
  • High‑capacity language generation

Limits

  • No vision support
  • License not specified
  • Requires large VRAM for higher quants

Best for

  • Developers building tool‑integrated assistants
  • Researchers testing large‑scale language models
  • Applications needing extensive context windows

Who it’s for. This model is suited for developers and researchers who need a large, tool‑aware language model and have the hardware resources to run it. It is ideal for building advanced conversational agents or conducting research on large‑scale LLM behavior.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K26.4 GB 29.6 GB
Too big Get file →
IQ3_XS29.3 GB 32.5 GB
Too big Get file →
IQ3_S30.9 GB 34.1 GB
Too big Get file →
Q3_K_S30.9 GB 34.1 GB
Too big Get file →
IQ3_M31.9 GB 35.1 GB
Too big Get file →
Q3_K_M34.3 GB 37.5 GB
Too big Get file →
Q3_K_L37.1 GB 40.3 GB
Too big Get file →
IQ4_XS38.3 GB 41.5 GB
Too big Get file →
Q4_K_S40.3 GB 43.5 GB
Too big Get file →
Q4_K_M42.5 GB 45.7 GB
Too big Get file →
Q5_K_S48.7 GB 51.8 GB
Too big Get file →
Q5_K_M49.9 GB 53.1 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (26.38 GB file, ~29.6 GB memory). For 16 GB VRAM, Q3_K_M (34.27 GB file, ~37.5 GB memory) or Q3_K_L (37.14 GB file, ~40.3 GB memory). For 32 GB VRAM, Q4_K_M (42.52 GB file, ~45.7 GB memory) or Q5_K_M (49.95 GB file, ~53.1 GB 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_K_M (42.5 GB file, about 45.7 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.

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

Architecturellama
Parameters70.6B
Layers80
Trained context131,072 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymradermacher
FamilyLlama
Downloads (HF)594
Last updated2024-08-17

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_M is 34.3 GB and 6 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 mradermacher/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 Hermes 3 Llama 3.1 70B on 8 GB VRAM?

Use the Q2_K quant, which requires about 29.6 GB of memory at 8 k context. 8 GB VRAM is insufficient for this model.

Does this model support vision tasks?

No, the model has no vision capability.

What context length does the model support?

It was trained with a context of 131072 tokens.

Other GGUFs of Hermes-3-Llama-3.1-70B-lorablated

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other large models

All large models →