GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

naimulislam999/LFM2.5-350M-Uncensored-GGUF overview

LFM 2.5 350M Uncensored GGUF This repository contains the GGUF conversions of the uncensored version of LiquidAI/LFM2.5 350M . The original model weights were …

gguftext-generationuncensoredlfmbase_model:LiquidAI/LFM2.5-350Mbase_model:quantized:LiquidAI/LFM2.5-350Mlicense:apache-2.0endpoints_compatibleregion:usconversational

Runs locally from ~172.8 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
0
Pipeline
text-generation

Repository Files & Downloads

18 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
model-IQ3_M.ggufGGUFIQ3_M175.2 MBDownload
model-IQ3_S.ggufGGUFIQ3_S172.8 MBDownload
model-IQ4_NL.ggufGGUFIQ4_NL210.3 MBDownload
model-IQ4_XS.ggufGGUFIQ4_XS202.0 MBDownload
model-Q3_K_L.ggufGGUFQ3_K_L193.6 MBDownload
model-Q3_K_M.ggufGGUFQ3_K_M184.2 MBDownload
model-Q3_K_S.ggufGGUFQ3_K_S172.8 MBDownload
model-Q4_0.ggufGGUFQ4_0209.2 MBDownload
model-Q4_1.ggufGGUFQ4_1226.3 MBDownload
model-Q4_K_M.ggufGGUFQ4_K_M218.7 MBDownload
model-Q4_K_S.ggufGGUFQ4_K_S210.5 MBDownload
model-Q5_0.ggufGGUFQ5_0243.4 MBDownload
model-Q5_1.ggufGGUFQ5_1260.5 MBDownload
model-Q5_K_M.ggufGGUFQ5_K_M248.3 MBDownload
model-Q5_K_S.ggufGGUFQ5_K_S243.4 MBDownload
model-Q6_K.ggufGGUFQ6_K279.8 MBDownload
model-Q8_0.ggufGGUFQ8_0361.7 MBDownload
model-f16.ggufGGUFF16678.5 MBDownload

Model Details

Model IDnaimulislam999/LFM2.5-350M-Uncensored-GGUF
Authornaimulislam999
Pipelinetext-generation
Licenseapache-2.0
Base modelLiquidAI/LFM2.5-350M
Last modified2026-08-29T07:50:55.000Z

Model README

---

base_model: LiquidAI/LFM2.5-350M

library_name: gguf

license: apache-2.0

tags:

  • text-generation
  • gguf
  • uncensored
  • lfm

---

LFM 2.5 350M Uncensored (GGUF)

This repository contains the GGUF conversions of the uncensored version of LiquidAI/LFM2.5-350M.

The original model weights were processed to remove alignment restrictions and then converted to .gguf format for efficient inference on CPU and Apple Silicon using llama.cpp and compatible frontends (e.g., LM Studio, Ollama, GPT4All).

Available Quants

This repository includes a comprehensive set of quantizations from extreme 1-bit compression up to full 16-bit precision.

| Quantization | Bits | Recommended Use Case |

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

| IQ1_S / IQ1_M | ~1.5 - 2 | Maximum memory savings. High perplexity loss expected on this small parameter size. |

| IQ2_XXS - IQ2_M | ~2 | Extreme compression. Usable, but degradation is noticeable. |

| IQ3_XXS - Q3_K_L | ~3 | High compression. Good for strictly limited memory environments. |

| IQ4_XS - Q4_K_M | ~4 | Recommended sweet spot. Great balance of memory usage and quality. |

| Q5_0 - Q5_K_M | ~5 | Near-lossless performance with modest memory savings. |

| Q6_K | ~6 | Effectively lossless. |

| Q8_0 | 8 | Fully lossless integer quantization. |

| F16 | 16 | Unquantized baseline. Highest quality, highest memory footprint. |

Usage with llama.cpp

You can run this model via the llama.cpp CLI. Replace <quant_type> with your desired precision (e.g., Q4_K_M).

./llama-cli -m model-<quant_type>.gguf -p "Your prompt here" -n 256

Run naimulislam999/LFM2.5-350M-Uncensored-GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models