---

license: other

license_name: lfm1.0

license_link: https://huggingface.co/LiquidAI/LFM2.5-230M/blob/main/LICENSE

base_model: hauser458original/lfm2.5-230m-code-math-v2

tags:

- lfm2

- lfm2.5

- liquid

- code

- math

- gguf

- llama.cpp

language:

- en

pipeline_tag: text-generation

---

LFM2.5-230M-Code-Math-v2-GGUF

GGUF quantized versions of hauser458original/lfm2.5-230m-code-math-v2, a code/math-focused fine-tune of LiquidAI/LFM2.5-230M (instruct). See the base fine-tune's model card for full training details, evaluation notes, and known limitations.

This model is a fixed version of hauser458original/lfm2.5-230m-code-math-GGUF, which fixed: negation (e.g. Which products do not contain dairy?), and also seen small improvements in code and math.

For use with llama.cpp, Ollama, LM Studio, or any other GGUF-compatible runtime.

Files

| File | Quantization | Approx. size | Notes |

|---|---|---|---|

| lfm2.5-230m-code-math-v2-F16.gguf | F16 | ~460 MB | Full precision, largest, highest fidelity |

| lfm2.5-230m-code-math-v2-Q8_0.gguf | Q8_0 | ~245 MB | Near-lossless, good default if size isn't a concern |

| lfm2.5-230m-code-math-v2-Q5_K_M.gguf | Q5_K_M | ~165 MB | Good balance of size/quality |

| lfm2.5-230m-code-math-v2-Q5_K_S.gguf | Q5_K_S | ~155 MB | Slightly smaller than Q5_K_M, marginal quality trade-off |

| lfm2.5-230m-code-math-v2-Q4_K_M.gguf | Q4_K_M | ~135 MB | Smallest here, most aggressive quantization, best for constrained/edge devices |

(Sizes are approximate — check actual file sizes in the repo.)

Usage

llama.cpp

./llama-cli -m lfm2.5-230m-code-math-v2-Q5_K_M.gguf -p "Write a Python function to check if a number is prime."

Ollama

ollama run hf.co/hauser458original/lfm2.5-230m-code-math-v2-GGUF:Q5_K_M

LM Studio

Search for hauser458original/lfm2.5-230m-code-math-v2-GGUF in the LM Studio model browser, or download a .gguf file directly and load it manually.

Which quant should I use?

• Q4_K_M: smallest footprint, best for very constrained devices (older phones, low-RAM edge hardware). Some quality loss vs. higher quants.
• Q5_K_S / Q5_K_M: good middle ground — recommended default for most laptop/desktop CPU inference.
• Q8_0: near-lossless, use if you have the RAM/storage headroom and want output as close as possible to the original safetensors model.
• F16: full precision GGUF, only needed if you plan to re-quantize yourself or want the highest possible fidelity in llama.cpp.

License

Inherits the LFM Open License v1.0 from the base model.