CoralLM 1b needs about 1.6 GB of memory at Q4_K_M (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 8 quants, from 0.5 GB (TQ2_0) to 2.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.1 GB.
CoralLM 1b is a 1.24B-parameter Llama model in GGUF format, quantized by NotHereNorThere. Its trained context length is 128K tokens. The repository has 8 quant files, from 0.5 GB (TQ2_0) to 2.5 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| TQ2_0 | 0.5 GB | 1.2 GB | Fits | Get file → | |
| Q3_K_M | 0.7 GB | 1.5 GB | Fits | Get file → | |
| Q4_K_S | 0.8 GB | 1.5 GB | Fits | Get file → | |
| Q4_K_M | 0.8 GB | 1.6 GB | Fits | Get file → | |
| Q5_K_S | 0.9 GB | 1.7 GB | Fits | Get file → | |
| Q5_K_M | 0.9 GB | 1.7 GB | Fits | Get file → | |
| Q6_K | 1.0 GB | 1.8 GB | Fits | Get file → | |
| F16 | 2.5 GB | 3.2 GB | Fits | Get file → |
What GPU do you need for CoralLM 1b?
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 F16 (2.5 GB file, about 3.2 GB in use).
Which CoralLM 1b quant should you choose?
Q4_K_M is the usual starting point for CoralLM 1b: it balances file size and quality well. Here it is a 0.8 GB file.
If memory is tight, the smallest file is TQ2_0 at 0.5 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about CoralLM 1b
How much VRAM does CoralLM 1b need?
About 1.6 GB at Q4_K_M with an 8K context window. That is the 0.8 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 CoralLM 1b on an 8 GB GPU?
Yes, with F16: the 2.5 GB file needs about 3.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of CoralLM 1b GGUF?
It depends on the quant: TQ2_0 is 0.5 GB, Q3_K_M is 0.7 GB, Q4_K_S is 0.8 GB, Q4_K_M is 0.8 GB, Q5_K_S is 0.9 GB, Q5_K_M is 0.9 GB and 2 more.
What context length does CoralLM 1b support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.1 GB at 32K.
Where can I download CoralLM 1b GGUF?
The files are on Hugging Face in the NotHereNorThere/CoralLM-1b repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does CoralLM 1b 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.