LMF 2.5 2B Code needs about 4.5 GB of memory at Q5_K_M (a 1.9 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.
LMF 2.5 2B Code – a 2.7B parameter code-focused LLM
LMF 2.5 2B Code is a 2.7B parameter model fine‑tuned for coding tasks. It supports a 131,072 token context window and is available in a Q5_K_M quantized GGUF file. The model is part of the Lfm family and builds on LFM2 architecture.
Good at
- Coding assistance
- Function calling
- Long‑context code generation
Limits
- No vision support
- No agentic coding
- License not specified
Best for
- Code completion
- Tool‑integrated coding workflows
- Long‑context code analysis
Who it’s for. Developers and researchers needing a lightweight code‑focused LLM that can run on local hardware. The model is suitable for on‑device inference with a 1.94 GB GGUF file.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_K_M | 1.9 GB | 4.5 GB | Fits | Get file → |
The Q5_K_M quantized file is 1.94 GB and requires about 4.5 GB of VRAM at an 8 k context. This is the only quant available, so it is the recommended choice for users with limited memory.
What GPU do you need for LMF 2.5 2B Code?
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 Q5_K_M (1.9 GB file, about 4.5 GB in use).
Which LMF 2.5 2B Code quant should you choose?
Q5_K_M (1.9 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about LMF 2.5 2B Code
How much VRAM does LMF 2.5 2B Code need?
About 4.5 GB at Q5_K_M with an 8K context window. That is the 1.9 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 LMF 2.5 2B Code on an 8 GB GPU?
Yes, with Q5_K_M: the 1.9 GB file needs about 4.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of LMF 2.5 2B Code GGUF?
It depends on the quant: Q5_K_M is 1.9 GB.
What context length does LMF 2.5 2B Code 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 LMF 2.5 2B Code GGUF?
The files are on Hugging Face in the bunnycore/LMF-2.5-2B-Code-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 LMF 2.5 2B Code on 8 GB VRAM?
Yes, the Q5_K_M quantized file requires approximately 4.5 GB of VRAM at an 8 k context, fitting within an 8 GB GPU.
Does this model support vision?
No, the model is text‑only and does not have vision capabilities.
What context length does it support?
It supports a 131,072 token context window.