Juno N Coder 25B A3B needs about 27.1 GB of memory at Q4_K_M (a 19.5 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 3 quants, from 19.5 GB (Q4_K_M) to 50.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 28.5 GB.
Juno N Coder 25B A3B is a 25.2B-parameter Juno model in GGUF format, quantized by locailabs. Its trained context length is 1024K tokens. The repository has 3 quant files, from 19.5 GB (Q4_K_M) to 50.5 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 19.5 GB | 27.1 GB | Too big | Get file → | |
| Q8_0 | 26.9 GB | 34.5 GB | Too big | Get file → | |
| BF16 | 50.5 GB | 58.1 GB | Too big | Get file → |
What GPU do you need for Juno N Coder 25B A3B?
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: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: the best quant that fits is Q4_K_M (19.5 GB file, about 27.1 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (26.9 GB file, about 34.5 GB in use).
Which Juno N Coder 25B A3B quant should you choose?
Q4_K_M is the usual starting point for Juno N Coder 25B A3B: it balances file size and quality well. Here it is a 19.5 GB file.
The Q8_0 file is 26.9 GB, about 1.4 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Juno N Coder 25B A3B
How much VRAM does Juno N Coder 25B A3B need?
About 27.1 GB at Q4_K_M with an 8K context window. That is the 19.5 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 Juno N Coder 25B A3B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 27.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Juno N Coder 25B A3B GGUF?
It depends on the quant: Q4_K_M is 19.5 GB, Q8_0 is 26.9 GB, BF16 is 50.5 GB.
What context length does Juno N Coder 25B A3B support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 7.1 GB at 8K and 28.5 GB at 32K.
Where can I download Juno N Coder 25B A3B GGUF?
The files are on Hugging Face in the locailabs/Juno-N-Coder-25B-A3B-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 Juno N Coder 25B A3B use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.