Nav3 1.5B 40k Model 256 needs about 1.7 GB of memory at Q4_K_M (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 1.0 GB (Q4_K_M) to 3.1 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.
Nav3 1.5B 40k Model 256 is a 1.54B-parameter Nav model in GGUF format, quantized by front-less. Its trained context length is 32K tokens. The repository has 2 quant files, from 1.0 GB (Q4_K_M) to 3.1 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 1.0 GB | 1.7 GB | Fits | Get file → | |
| — | 3.1 GB | 3.8 GB | Fits | Get file → |
What GPU do you need for Nav3 1.5B 40k Model 256?
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 the main file (3.1 GB file, about 3.8 GB in use).
Which Nav3 1.5B 40k Model 256 quant should you choose?
Q4_K_M is the usual starting point for Nav3 1.5B 40k Model 256: it balances file size and quality well. Here it is a 1.0 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Nav3 1.5B 40k Model 256
How much VRAM does Nav3 1.5B 40k Model 256 need?
About 1.7 GB at Q4_K_M with an 8K context window. That is the 1.0 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 Nav3 1.5B 40k Model 256 on an 8 GB GPU?
Yes, with the smaller files: the 3.1 GB file needs about 3.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Nav3 1.5B 40k Model 256 GGUF?
It depends on the quant: Q4_K_M is 1.0 GB, file is 3.1 GB.
What context length does Nav3 1.5B 40k Model 256 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.9 GB at 32K.
Where can I download Nav3 1.5B 40k Model 256 GGUF?
The files are on Hugging Face in the front-less/nav3-1.5B-40k-model-256 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.