Mermaid Llama 3 6B Pruned needs about 4.8 GB of memory at IQ4_XS (a 3.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 8 quants, from 2.8 GB (IQ3_XS) to 12.6 GB (F16).
Mermaid Llama 3 6B Pruned is a 6.29B-parameter Llama model in GGUF format, quantized by mradermacher. Its trained context length is 8K tokens. The repository has 8 quant files, from 2.8 GB (IQ3_XS) to 12.6 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_XS | 2.8 GB | 4.1 GB | Fits | Get file → | |
| Q3_K_S | 2.9 GB | 4.2 GB | Fits | Get file → | |
| Q3_K_M | 3.2 GB | 4.5 GB | Fits | Get file → | |
| IQ4_XS | 3.5 GB | 4.8 GB | Fits | Get file → | |
| Q5_K_S | 4.4 GB | 5.7 GB | Fits | Get file → | |
| Q5_K_M | 4.5 GB | 5.8 GB | Fits | Get file → | |
| Q8_0 | 6.7 GB | 8.0 GB | Tight | Get file → | |
| F16 | 12.6 GB | 13.9 GB | Too big | Get file → |
What GPU do you need for Mermaid Llama 3 6B Pruned?
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: the best quant that fits is Q5_K_M (4.5 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (6.7 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (6.7 GB file, about 8.0 GB in use).
- 16 GB VRAM: the best quant that fits is F16 (12.6 GB file, about 13.9 GB in use).
Which Mermaid Llama 3 6B Pruned quant should you choose?
IQ4_XS (3.5 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is IQ3_XS at 2.8 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Mermaid Llama 3 6B Pruned
How much VRAM does Mermaid Llama 3 6B Pruned need?
About 4.8 GB at IQ4_XS with an 8K context window. That is the 3.5 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 Mermaid Llama 3 6B Pruned on an 8 GB GPU?
Yes, with Q8_0: the 6.7 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 Mermaid Llama 3 6B Pruned GGUF?
It depends on the quant: IQ3_XS is 2.8 GB, Q3_K_S is 2.9 GB, Q3_K_M is 3.2 GB, IQ4_XS is 3.5 GB, Q5_K_S is 4.4 GB, Q5_K_M is 4.5 GB and 2 more.
What context length does Mermaid Llama 3 6B Pruned support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.8 GB at 8K and 0.8 GB at 8K.
Where can I download Mermaid Llama 3 6B Pruned GGUF?
The files are on Hugging Face in the mradermacher/Mermaid-Llama-3-6B-Pruned-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 Mermaid Llama 3 6B Pruned use?
Hugging Face lists the license as cc-by-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.