nyun-c1-llama3-60B needs about 39.1 GB of memory at Q4_K_M (a 36.3 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 21 quants, from 13.2 GB (IQ1_S) to 49.5 GB (Q6_K).
nyun-c1-llama3-60B is a 60.3B-parameter Llama model in GGUF format, quantized by mradermacher. Its trained context length is 8K tokens. The repository has 21 quant files, from 13.2 GB (IQ1_S) to 49.5 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 13.2 GB | 16.0 GB | Too big | Get file → | |
| IQ1_M | 14.4 GB | 17.2 GB | Too big | Get file → | |
| IQ2_XXS | 16.4 GB | 19.2 GB | Too big | Get file → | |
| IQ2_XS | 18.1 GB | 20.9 GB | Too big | Get file → | |
| IQ2_S | 19.1 GB | 21.8 GB | Too big | Get file → | |
| IQ2_M | 20.7 GB | 23.4 GB | Too big | Get file → | |
| Q2_K | 22.5 GB | 25.3 GB | Too big | Get file → | |
| IQ3_XXS | 23.5 GB | 26.2 GB | Too big | Get file → | |
| IQ3_XS | 25.0 GB | 27.8 GB | Too big | Get file → | |
| Q3_K_S | 26.3 GB | 29.1 GB | Too big | Get file → | |
| IQ3_S | 26.4 GB | 29.2 GB | Too big | Get file → | |
| IQ3_M | 27.3 GB | 30.0 GB | Too big | Get file → | |
| Q3_K_M | 29.2 GB | 32.0 GB | Too big | Get file → | |
| Q3_K_L | 31.8 GB | 34.5 GB | Too big | Get file → | |
| IQ4_XS | 32.4 GB | 35.2 GB | Too big | Get file → | |
| Q4_0 | 34.3 GB | 37.1 GB | Too big | Get file → | |
| Q4_K_S | 34.4 GB | 37.2 GB | Too big | Get file → | |
| Q4_K_M | 36.3 GB | 39.1 GB | Too big | Get file → | |
| Q5_K_S | 41.6 GB | 44.4 GB | Too big | Get file → | |
| Q5_K_M | 42.7 GB | 45.5 GB | Too big | Get file → | |
| Q6_K | 49.5 GB | 52.2 GB | Too big | Get file → |
What GPU do you need for nyun-c1-llama3-60B?
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 IQ1_S (13.2 GB file, about 16.0 GB in use).
- 24 GB VRAM: the best quant that fits is IQ2_M (20.7 GB file, about 23.4 GB in use).
- 32 GB VRAM: the best quant that fits is Q3_K_M (29.2 GB file, about 32.0 GB in use).
- 48 GB VRAM: the best quant that fits is Q5_K_M (42.7 GB file, about 45.5 GB in use).
Which nyun-c1-llama3-60B quant should you choose?
Q4_K_M is the usual starting point for nyun-c1-llama3-60B: it balances file size and quality well. Here it is a 36.3 GB file.
If memory is tight, the smallest file is IQ1_S at 13.2 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 nyun-c1-llama3-60B
How much VRAM does nyun-c1-llama3-60B need?
About 39.1 GB at Q4_K_M with an 8K context window. That is the 36.3 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 nyun-c1-llama3-60B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 16.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of nyun-c1-llama3-60B GGUF?
It depends on the quant: IQ1_S is 13.2 GB, IQ1_M is 14.4 GB, IQ2_XXS is 16.4 GB, IQ2_XS is 18.1 GB, IQ2_S is 19.1 GB, IQ2_M is 20.7 GB and 15 more.
What context length does nyun-c1-llama3-60B support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.3 GB at 8K and 2.3 GB at 8K.
Where can I download nyun-c1-llama3-60B GGUF?
The files are on Hugging Face in the mradermacher/nyun-c1-llama3-60B-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 nyun-c1-llama3-60B use?
Hugging Face lists the license as llama3. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.