Impish LLAMA 6.84B iMatrix needs about 5.1 GB of memory at IQ2_M (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 12 quants, from 1.6 GB (IQ1_S) to 4.0 GB (IQ4_NL). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
Impish LLAMA 6.84B iMatrix is a 6.84B-parameter Llama model in GGUF format, quantized by SicariusSicariiStuff. Its trained context length is 128K tokens. The repository has 12 quant files, from 1.6 GB (IQ1_S) to 4.0 GB (IQ4_NL).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 1.6 GB | 4.3 GB | Fits | Get file → | |
| IQ1_M | 1.8 GB | 4.4 GB | Fits | Get file → | |
| IQ2_XXS | 2.0 GB | 4.6 GB | Fits | Get file → | |
| IQ2_XS | 2.2 GB | 4.8 GB | Fits | Get file → | |
| IQ2_S | 2.3 GB | 4.9 GB | Fits | Get file → | |
| IQ2_M | 2.5 GB | 5.1 GB | Fits | Get file → | |
| IQ3_XXS | 2.7 GB | 5.4 GB | Fits | Get file → | |
| IQ3_XS | 2.9 GB | 5.6 GB | Fits | Get file → | |
| IQ3_S | 3.1 GB | 5.7 GB | Fits | Get file → | |
| IQ3_M | 3.2 GB | 5.9 GB | Fits | Get file → | |
| IQ4_XS | 3.8 GB | 6.4 GB | Fits | Get file → | |
| IQ4_NL | 4.0 GB | 6.6 GB | Fits | Get file → |
What GPU do you need for Impish LLAMA 6.84B iMatrix?
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 IQ3_M (3.2 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is IQ4_NL (4.0 GB file, about 6.6 GB in use).
Which Impish LLAMA 6.84B iMatrix quant should you choose?
IQ2_M (2.5 GB) is the middle option in this repository. 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.
If memory is tight, the smallest file is IQ1_S at 1.6 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
Source
Frequently asked questions about Impish LLAMA 6.84B iMatrix
How much VRAM does Impish LLAMA 6.84B iMatrix need?
About 5.1 GB at IQ2_M with an 8K context window. That is the 2.5 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 Impish LLAMA 6.84B iMatrix on an 8 GB GPU?
Yes, with IQ4_NL: the 4.0 GB file needs about 6.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Impish LLAMA 6.84B iMatrix GGUF?
It depends on the quant: IQ1_S is 1.6 GB, IQ1_M is 1.8 GB, IQ2_XXS is 2.0 GB, IQ2_XS is 2.2 GB, IQ2_S is 2.3 GB, IQ2_M is 2.5 GB and 6 more.
What context length does Impish LLAMA 6.84B iMatrix support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download Impish LLAMA 6.84B iMatrix GGUF?
The files are on Hugging Face in the SicariusSicariiStuff/Impish_LLAMA_6.84B_iMatrix repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Impish LLAMA 6.84B iMatrix use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.