Llama 3.2 3b KermesRed V3.4 needs about 4.1 GB of memory at Q6_K (a 2.6 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 5 quants, from 1.9 GB (Q4_K_S) to 6.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
Llama 3.2 3b KermesRed V3.4 is a 3.21B-parameter Llama model in GGUF format, quantized by Nexesenex. Its trained context length is 128K tokens. The repository has 5 quant files, from 1.9 GB (Q4_K_S) to 6.4 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_S | 1.9 GB | 3.4 GB | Fits | Get file → | |
| Q5_K_S | 2.3 GB | 3.7 GB | Fits | Get file → | |
| Q6_K | 2.6 GB | 4.1 GB | Fits | Get file → | |
| Q8_0 | 3.4 GB | 4.9 GB | Fits | Get file → | |
| F16 | 6.4 GB | 7.9 GB | Tight | Get file → |
What GPU do you need for Llama 3.2 3b KermesRed V3.4?
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_S (2.3 GB file, about 3.7 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.4 GB file, about 4.9 GB in use).
- 8 GB VRAM: the best quant that fits is F16 (6.4 GB file, about 7.9 GB in use).
Which Llama 3.2 3b KermesRed V3.4 quant should you choose?
Q6_K (2.6 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
If memory is tight, the smallest file is Q4_K_S at 1.9 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Llama 3.2 3b KermesRed V3.4
How much VRAM does Llama 3.2 3b KermesRed V3.4 need?
About 4.1 GB at Q6_K with an 8K context window. That is the 2.6 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 Llama 3.2 3b KermesRed V3.4 on an 8 GB GPU?
Yes, with F16: the 6.4 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Llama 3.2 3b KermesRed V3.4 GGUF?
It depends on the quant: Q4_K_S is 1.9 GB, Q5_K_S is 2.3 GB, Q6_K is 2.6 GB, Q8_0 is 3.4 GB, F16 is 6.4 GB.
What context length does Llama 3.2 3b KermesRed V3.4 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 Llama 3.2 3b KermesRed V3.4 GGUF?
The files are on Hugging Face in the Nexesenex/Llama_3.2_3b_KermesRed_V3.4-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 Llama 3.2 3b KermesRed V3.4 use?
Hugging Face lists the license as llama3.2. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.