chargoddard llama 2 34b uncode iMat needs about 18.4 GB of memory at Q3_K_M (a 16.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 6 quants, from 12.5 GB (Q2_K) to 35.9 GB (Q8_0).
chargoddard llama 2 34b uncode iMat is a 33.7B-parameter Llama model in GGUF format, quantized by Nexesenex. Its trained context length is 16K tokens. The repository has 6 quant files, from 12.5 GB (Q2_K) to 35.9 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 12.5 GB | 14.6 GB | Too big | Get file → | |
| Q3_K_S | 14.6 GB | 16.7 GB | Too big | Get file → | |
| Q3_K_M | 16.3 GB | 18.4 GB | Too big | Get file → | |
| Q4_K_S | 19.2 GB | 21.3 GB | Too big | Get file → | |
| Q5_K_S | 23.2 GB | 25.3 GB | Too big | Get file → | |
| Q8_0 | 35.9 GB | 38.0 GB | Too big | Get file → |
What GPU do you need for chargoddard llama 2 34b uncode iMat?
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: the best quant that fits is Q2_K (12.5 GB file, about 14.6 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_S (19.2 GB file, about 21.3 GB in use).
- 32 GB VRAM: the best quant that fits is Q5_K_S (23.2 GB file, about 25.3 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (35.9 GB file, about 38.0 GB in use).
Which chargoddard llama 2 34b uncode iMat quant should you choose?
Q3_K_M (16.3 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is Q2_K at 12.5 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
Frequently asked questions about chargoddard llama 2 34b uncode iMat
How much VRAM does chargoddard llama 2 34b uncode iMat need?
About 18.4 GB at Q3_K_M with an 8K context window. That is the 16.3 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 chargoddard llama 2 34b uncode iMat on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 14.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of chargoddard llama 2 34b uncode iMat GGUF?
It depends on the quant: Q2_K is 12.5 GB, Q3_K_S is 14.6 GB, Q3_K_M is 16.3 GB, Q4_K_S is 19.2 GB, Q5_K_S is 23.2 GB, Q8_0 is 35.9 GB.
What context length does chargoddard llama 2 34b uncode iMat support?
The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 1.6 GB at 8K and 3.2 GB at 16K.
Where can I download chargoddard llama 2 34b uncode iMat GGUF?
The files are on Hugging Face in the Nexesenex/chargoddard_llama-2-34b-uncode-iMat.GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.