DrMoriarty0/LFM2.5-8B-A1B-GGUF overview
This model quanted with modified APEX method https://github.com/DrMoriarty/apex quant Quality comparison: |Quant|PPL Q /PPL base |Mean KLD|Median KLD|99.0% KLD…
Runs locally from ~16.6 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| LFM2.5-8B-A1B-imatrix.gguf | GGUF | GGUF | 16.6 MB | Download |
Model Details
| Model ID | DrMoriarty0/LFM2.5-8B-A1B-GGUF |
|---|---|
| Author | DrMoriarty0 |
| Pipeline | — |
| License | other |
| Base model | LiquidAI/LFM2.5-8B-A1B |
| Last modified | 2026-09-18T08:47:46.000Z |
Model README
---
license: other
license_name: lfm1.0
license_link: LICENSE
base_model:
- LiquidAI/LFM2.5-8B-A1B
---
This model quanted with modified APEX method
Quality comparison:
|Quant|PPL(Q)/PPL(base)|Mean KLD|Median KLD|99.0% KLD|Δp RMS|Same top p|Size (Gb)|
|-----|----------------|--------|----------|---------|------|----------|---------|
|BF16|1,0|0|0|0|0%|100%|16,162|
|Q8_0|1,005939|0,0225|0,0016|0,37|3,275 %|95,556 %|8,593|
|i-Tier1|1,006857|0,0285|0,0029|0,10|3,745 %|94,767 %|6,845|
All other quants have very poor quality near to unusable.
Run DrMoriarty0/LFM2.5-8B-A1B-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models