Llamion 14b Chat needs about 16.0 GB of memory at Q4_K_M (a 8.8 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 22 quants, from 3.4 GB (IQ1_S) to 11.9 GB (Q6_K).
Llamion 14b Chat is a 14.5B-parameter Llamion model in GGUF format, quantized by mradermacher. Its trained context length is 4K tokens. The repository has 22 quant files, from 3.4 GB (IQ1_S) to 11.9 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 3.4 GB | 7.2 GB | Tight | Get file → | |
| IQ1_M | 3.6 GB | 7.5 GB | Tight | Get file → | |
| IQ2_XXS | 4.1 GB | 7.9 GB | Tight | Get file → | |
| IQ2_XS | 4.4 GB | 8.3 GB | Too big | Get file → | |
| IQ2_S | 4.8 GB | 8.6 GB | Too big | Get file → | |
| Q2_K_S | 5.1 GB | 8.9 GB | Too big | Get file → | |
| IQ2_M | 5.1 GB | 9.0 GB | Too big | Get file → | |
| Q2_K | 5.5 GB | 9.4 GB | Too big | Get file → | |
| IQ3_XXS | 5.6 GB | 9.5 GB | Too big | Get file → | |
| IQ3_XS | 6.1 GB | 9.9 GB | Too big | Get file → | |
| IQ3_S | 6.4 GB | 10.3 GB | Too big | Get file → | |
| Q3_K_S | 6.4 GB | 10.3 GB | Too big | Get file → | |
| IQ3_M | 6.7 GB | 10.6 GB | Too big | Get file → | |
| Q3_K_M | 7.1 GB | 11.0 GB | Too big | Get file → | |
| Q3_K_L | 7.8 GB | 11.6 GB | Too big | Get file → | |
| IQ4_XS | 7.8 GB | 11.7 GB | Too big | Get file → | |
| Q4_0 | 8.3 GB | 12.2 GB | Too big | Get file → | |
| Q4_K_S | 8.3 GB | 12.2 GB | Too big | Get file → | |
| Q4_K_M | 8.8 GB | 12.7 GB | Too big | Get file → | |
| Q5_K_S | 10.0 GB | 13.9 GB | Too big | Get file → | |
| Q5_K_M | 10.3 GB | 14.2 GB | Too big | Get file → | |
| Q6_K | 11.9 GB | 15.8 GB | Too big | Get file → |
What GPU do you need for Llamion 14b Chat?
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: the best quant that fits is IQ2_S (4.8 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_M (8.8 GB file, about 16.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (11.9 GB file, about 19.1 GB in use).
Which Llamion 14b Chat quant should you choose?
Q4_K_M is the usual starting point for Llamion 14b Chat: it balances file size and quality well. Here it is a 8.8 GB file.
If memory is tight, the smallest file is IQ1_S at 3.4 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 Llamion 14b Chat
How much VRAM does Llamion 14b Chat need?
About 16.0 GB at Q4_K_M with an 8K context window. That is the 8.8 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 Llamion 14b Chat on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Llamion 14b Chat GGUF?
It depends on the quant: IQ1_S is 3.4 GB, IQ1_M is 3.6 GB, IQ2_XXS is 4.1 GB, IQ2_XS is 4.4 GB, IQ2_S is 4.8 GB, Q2_K_S is 5.1 GB and 16 more.
What context length does Llamion 14b Chat support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.
Where can I download Llamion 14b Chat GGUF?
The files are on Hugging Face in the mradermacher/llamion-14b-chat-i1-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 Llamion 14b Chat 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.