hauser458original/lfm2.5-350m-code-math-GGUF overview
LFM2.5 350M Code Math GGUF GGUF quantized versions of hauser458original/lfm2.5 350m code math https://huggingface.co/hauser458original/lfm2.5 350m code math , …
Runs locally from ~218.7 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| lfm2.5-350m-code-math-F16.gguf | GGUF | F16 | 678.5 MB | Download |
| lfm2.5-350m-code-math-Q4_K_M.gguf | GGUF | Q4_K_M | 218.7 MB | Download |
| lfm2.5-350m-code-math-Q5_K_M.gguf | GGUF | Q5_K_M | 248.3 MB | Download |
| lfm2.5-350m-code-math-Q5_K_S.gguf | GGUF | Q5_K_S | 243.4 MB | Download |
| lfm2.5-350m-code-math-Q8_0.gguf | GGUF | Q8_0 | 361.6 MB | Download |
Model Details
| Model ID | hauser458original/lfm2.5-350m-code-math-GGUF |
|---|---|
| Author | hauser458original |
| Pipeline | text-generation |
| License | other |
| Base model | hauser458original/lfm2.5-350m-code-math |
| Last modified | 2026-07-13T12:34:40.000Z |
Model README
---
license: other
license_name: lfm1.0
license_link: https://huggingface.co/LiquidAI/LFM2.5-350M/blob/main/LICENSE
base_model: hauser458original/lfm2.5-350m-code-math
tags:
- lfm2
- lfm2.5
- liquid
- code
- math
- gguf
- llama.cpp
language:
- en
pipeline_tag: text-generation
---
LFM2.5-350M-Code-Math-GGUF
GGUF quantized versions of hauser458original/lfm2.5-350m-code-math, a multi-language code + math fine-tune of LiquidAI/LFM2.5-350M (instruct) with balanced general chat retention. See the base fine-tune's model card for full training details, evaluation notes, and known limitations.
For use with llama.cpp, Ollama, LM Studio, or any other GGUF-compatible runtime.
Files
| File | Quantization | Approx. size | Notes |
|---|---|---|---|
| lfm2.5-350m-code-math-F16.gguf | F16 | ~700 MB | Full precision, largest, highest fidelity |
| lfm2.5-350m-code-math-Q8_0.gguf | Q8_0 | ~375 MB | Near-lossless, good default if size isn't a concern |
| lfm2.5-350m-code-math-Q5_K_M.gguf | Q5_K_M | ~250 MB | Good balance of size/quality |
| lfm2.5-350m-code-math-Q5_K_S.gguf | Q5_K_S | ~235 MB | Slightly smaller than Q5_K_M, marginal quality trade-off |
| lfm2.5-350m-code-math-Q4_K_M.gguf | Q4_K_M | ~205 MB | Smallest here, most aggressive quantization, best for constrained devices |
(Sizes are approximate — check actual file sizes in the repo.)
Usage
llama.cpp
./llama-cli -m lfm2.5-350m-code-math-Q5_K_S.gguf -t 8 --temperature 0.5 --top-p 0.9 --top-k 50 --min-p 0.05 --repeat-penalty 1.1Ollama
ollama run hf.co/hauser458original/lfm2.5-350m-code-math-GGUF:Q5_K_SLM Studio
Search for hauser458original/lfm2.5-350m-code-math-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. Some quality loss vs. higher quants.
- Q5_K_S / Q5_K_M: recommended default for most laptop/desktop CPU inference. Best speed/quality tradeoff.
- Q8_0: near-lossless, use if you have the RAM/storage headroom.
- F16: full precision GGUF, only needed if you plan to re-quantize yourself.
License
Inherits the LFM Open License v1.0 from the base model.
Run hauser458original/lfm2.5-350m-code-math-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models