LL

Hermes 3 Llama 3.2 3b Base Fft Chatml Rerun 8xh100 E4 2024 11 24 4k Steps

LlamaGGUF by NousResearchUpdated 2024-12-18
Download on Hugging Face
Parameters3.21B
Context128K
Layers28
Architecturellama
Smallest quant2.0 GB
Quick answer

Hermes 3 Llama 3.2 3b Base Fft Chatml Rerun 8xh100 E4 2024 11 24 4k Steps needs about 3.5 GB of memory at Q4_K_M (a 2.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 2.0 GB (Q4_K_M) to 3.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Hermes 3 Llama 3.2 3B – a fine‑tuned generalist assistant

Hermes 3 Llama 3.2 3B is a 3 billion‑parameter fine‑tune of Llama‑3.2. It supports roleplay, tools, and multi‑turn conversation with ChatML prompts. The model was trained on H100 GPUs at LambdaLabs.

Good at

  • ChatML prompt compatibility
  • Roleplay and agentic tasks
  • Structured function calling

Limits

  • No vision support
  • Requires 8 k context for memory estimates
  • License is llama3

Best for

  • Chatbot development
  • Tool‑integrated assistants
  • Code generation tasks

Who it’s for. Developers building conversational agents that need steering and structured output. The model is suitable for applications requiring multi‑turn dialogue and function calling.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.0 GB 3.5 GB
Fits Get file →
Q5_K_M2.3 GB 3.8 GB
Fits Get file →
Q6_K2.6 GB 4.1 GB
Fits Get file →
Q8_03.4 GB 4.9 GB
Fits Get file →

For 8 GB VRAM, Q4_K_M (2.02 GB, ~3.5 GB RAM) is recommended. If 12 GB VRAM is available, Q5_K_M (2.32 GB, ~3.8 GB RAM) offers a balance of quality and memory. Larger Q6_K or Q8_0 require more than 16 GB VRAM.

What GPU do you need for Hermes 3 Llama 3.2 3b Base Fft Chatml Rerun 8xh100 E4 2024 11 24 4k Steps?

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: the best quant that fits is Q5_K_M (2.3 GB file, about 3.8 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.4 GB file, about 4.9 GB in use).

Which Hermes 3 Llama 3.2 3b Base Fft Chatml Rerun 8xh100 E4 2024 11 24 4k Steps quant should you choose?

Q4_K_M is the usual starting point for Hermes 3 Llama 3.2 3b Base Fft Chatml Rerun 8xh100 E4 2024 11 24 4k Steps: it balances file size and quality well. Here it is a 2.0 GB file.

The Q8_0 file is 3.4 GB, about 1.7 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.21B
Layers28
Trained context131,072 tokens
KV cache (fp16)112 KB per token

Source

Quantized byNousResearch
FamilyLlama
Licensellama3
Downloads (HF)7,929
Last updated2024-12-18

Frequently asked questions about Hermes 3 Llama 3.2 3b Base Fft Chatml Rerun 8xh100 E4 2024 11 24 4k Steps

How much VRAM does Hermes 3 Llama 3.2 3b Base Fft Chatml Rerun 8xh100 E4 2024 11 24 4k Steps need?

About 3.5 GB at Q4_K_M with an 8K context window. That is the 2.0 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 Hermes 3 Llama 3.2 3b Base Fft Chatml Rerun 8xh100 E4 2024 11 24 4k Steps on an 8 GB GPU?

Yes, with Q8_0: the 3.4 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Hermes 3 Llama 3.2 3b Base Fft Chatml Rerun 8xh100 E4 2024 11 24 4k Steps GGUF?

It depends on the quant: Q4_K_M is 2.0 GB, Q5_K_M is 2.3 GB, Q6_K is 2.6 GB, Q8_0 is 3.4 GB.

What context length does Hermes 3 Llama 3.2 3b Base Fft Chatml Rerun 8xh100 E4 2024 11 24 4k Steps support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download Hermes 3 Llama 3.2 3b Base Fft Chatml Rerun 8xh100 E4 2024 11 24 4k Steps GGUF?

The files are on Hugging Face in the NousResearch/Hermes-3-Llama-3.2-3B-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 3.2 3b Base Fft Chatml Rerun 8xh100 E4 2024 11 24 4k Steps 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?

Yes, using the Q4_K_M quantized file which is 2.02 GB and requires about 3.5 GB of VRAM at 8 k context.

Does Hermes 3 support vision?

No, the model does not have vision capabilities.

What prompt format does Hermes 3 use?

Hermes 3 uses ChatML prompts, compatible with OpenAI’s ChatGPT API.

Similar models

Browse all →

More from NousResearch

All by NousResearch →

More Llama models

All Llama →

Other tiny models

All tiny models →