AmberChat needs about 8.9 GB of memory at Q4_K_M (a 4.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 22 quants, from 1.3 GB (IQ4_NL) to 7.2 GB (Q8_0).
AmberChat is a 6.74B-parameter Amberchat model in GGUF format, quantized by RichardErkhov. Its trained context length is 2K tokens. The repository has 22 quant files, from 1.3 GB (IQ4_NL) to 7.2 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_NL | 1.3 GB | 2.9 GB | Fits | Get file → | |
| Q5_K_S | 1.8 GB | 3.3 GB | Fits | Get file → | |
| Q2_K | 2.5 GB | 4.1 GB | Fits | Get file → | |
| IQ3_XS | 2.8 GB | 4.4 GB | Fits | Get file → | |
| IQ3_S | 2.9 GB | 4.5 GB | Fits | Get file → | |
| Q3_K_S | 2.9 GB | 4.5 GB | Fits | Get file → | |
| IQ3_M | 3.1 GB | 4.7 GB | Fits | Get file → | |
| Q3_K | 3.3 GB | 4.9 GB | Fits | Get file → | |
| Q3_K_M | 3.3 GB | 4.9 GB | Fits | Get file → | |
| Q3_K_L | 3.6 GB | 5.2 GB | Fits | Get file → | |
| IQ4_XS | 3.6 GB | 5.2 GB | Fits | Get file → | |
| Q4_0 | 3.8 GB | 5.4 GB | Fits | Get file → | |
| Q4_K_S | 3.9 GB | 5.4 GB | Fits | Get file → | |
| Q4_K | 4.1 GB | 5.7 GB | Fits | Get file → | |
| Q4_K_M | 4.1 GB | 5.7 GB | Fits | Get file → | |
| Q4_1 | 4.2 GB | 5.8 GB | Fits | Get file → | |
| Q5_0 | 4.7 GB | 6.2 GB | Fits | Get file → | |
| Q5_K | 4.8 GB | 6.4 GB | Fits | Get file → | |
| Q5_K_M | 4.8 GB | 6.4 GB | Fits | Get file → | |
| Q5_1 | 5.1 GB | 6.6 GB | Fits | Get file → | |
| Q6_K | 5.5 GB | 7.1 GB | Fits | Get file → | |
| Q8_0 | 7.2 GB | 8.7 GB | Too big | Get file → |
What GPU do you need for AmberChat?
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: the best quant that fits is IQ3_M (3.1 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 12.0 GB in use).
Which AmberChat quant should you choose?
Q4_K_M is the usual starting point for AmberChat: it balances file size and quality well. Here it is a 4.1 GB file.
The Q8_0 file is 7.2 GB, about 1.8 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.
If memory is tight, the smallest file is IQ4_NL at 1.3 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
Source
Frequently asked questions about AmberChat
How much VRAM does AmberChat need?
About 8.9 GB at Q4_K_M with an 8K context window. That is the 4.1 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 AmberChat on an 8 GB GPU?
Yes, with IQ3_M: the 3.1 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 AmberChat GGUF?
It depends on the quant: IQ4_NL is 1.3 GB, Q5_K_S is 1.8 GB, Q2_K is 2.5 GB, IQ3_XS is 2.8 GB, IQ3_S is 2.9 GB, Q3_K_S is 2.9 GB and 16 more.
What context length does AmberChat support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 4.3 GB at 8K and 1.1 GB at 2K.
Where can I download AmberChat GGUF?
The files are on Hugging Face in the RichardErkhov/LLM360_-_AmberChat-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 AmberChat 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.