fuse 1 Lite needs about 5.9 GB of memory at Q4_K_M (a 3.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 3.4 GB (Q4_K_M) to 11.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.
Fuse 1 Lite – 5.72B parameter LLM with MoE and 131072 token context
Fuse 1 Lite is a 5.72 billion parameter language model built on the Fuse3 architecture. It supports reasoning and tool usage and offers a large 131072 token context window. The model is distributed in GGUF format for llama.cpp integration.
Good at
- Reasoning tasks
- Tool integration
- Large context handling
Limits
- No vision support
- License not specified
- Requires llama.cpp with Fuse3 support
Best for
- Chatbots needing long context
- Tool‑enabled applications
- Research on MoE models
Who it’s for. Developers and researchers who need a moderately sized LLM with a large context window and tool‑usage capabilities. The model is suitable for applications that can run llama.cpp with Fuse3 support.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 3.4 GB | 5.9 GB | Fits | Get file → | |
| Q4_K_M | 3.4 GB | 5.9 GB | Fits | Get file → | |
| F16 | 11.4 GB | 14.0 GB | Too big | Get file → |
For 8 GB VRAM, use the Q4_K_M quantization (3.37 GB file, ~5.9 GB memory at 8 k context). For 16 GB VRAM, the F16 quant (11.45 GB file, ~14 GB memory at 8 k context) provides higher precision. Memory estimates are approximate.
What GPU do you need for fuse 1 Lite?
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: the best quant that fits is Q4_K_M (3.4 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q4_K_M (3.4 GB file, about 5.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_K_M (3.4 GB file, about 5.9 GB in use).
- 16 GB VRAM: the best quant that fits is F16 (11.4 GB file, about 14.0 GB in use).
Which fuse 1 Lite quant should you choose?
Q4_K_M is the usual starting point for fuse 1 Lite: it balances file size and quality well. Here it is a 3.4 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about fuse 1 Lite
How much VRAM does fuse 1 Lite need?
About 5.9 GB at Q4_K_M with an 8K context window. That is the 3.4 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 fuse 1 Lite on an 8 GB GPU?
Yes, with Q4_K_M: the 3.4 GB file needs about 5.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of fuse 1 Lite GGUF?
It depends on the quant: Q4_K_M is 3.4 GB, Q4_K_M is 3.4 GB, F16 is 11.4 GB.
What context length does fuse 1 Lite support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.0 GB at 8K and 8.1 GB at 32K.
Where can I download fuse 1 Lite GGUF?
The files are on Hugging Face in the Akahsizrr/fuse-1-Lite-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run Fuse 1 Lite on 8 GB VRAM?
Yes, the Q4_K_M quantization uses 3.37 GB and requires about 5.9 GB of VRAM at 8 k context.
Does Fuse 1 Lite support vision tasks?
No, the model has no vision capabilities.
What is the context length of Fuse 1 Lite?
The model supports a context length of 131072 tokens.