1bit-MONSTER/LFM2.5-8B-A1B-GGUF overview
LFM2.5 8B A1B — GGUF Q4 K M Liquid AI's own Q4 K M GGUF for their hybrid LFM2 MoE 8B total, ~1B active , re hosted with measured performance for the 1bit engin…
Runs locally from ~4.80 GB disk (8 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| LFM2.5-8B-A1B-Q4_K_M.gguf | GGUF | Q4_K_M | 4.80 GB | Download |
Model Details
| Model ID | 1bit-MONSTER/LFM2.5-8B-A1B-GGUF |
|---|---|
| Author | 1bit-MONSTER |
| Pipeline | — |
| License | other |
| Base model | LiquidAI/LFM2.5-8B-A1B |
| Last modified | 2026-09-26T15:37:42.000Z |
Model README
---
license: other
license_name: lfm1.0
license_link: LICENSE
base_model:
- LiquidAI/LFM2.5-8B-A1B
tags:
- gguf
- moe
---
LFM2.5-8B-A1B — GGUF (Q4_K_M)
Liquid AI's own Q4_K_M GGUF for their hybrid LFM2 MoE (8B total, ~1B active), re-hosted
with measured performance for the 1bit engine
on Strix Halo.
Licensed under the LFM Open License v1.0 — free for non-commercial/research
use and commercial use below $10M annual revenue; above that threshold a separate
license from Liquid AI is required.
Contents
LFM2.5-8B-A1B-Q4_K_M.gguf
Measured performance (Strix Halo, Vulkan)
pp512: 3448 tok/s · tg128: 166 tok/s
Running it
1bit serve -m LFM2.5-8B-A1B-Q4_K_M.gguf --device vulkanAttribution
- Model and quantization: LiquidAI/LFM2.5-8B-A1B-GGUF.
Run 1bit-MONSTER/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