LFM2.5-1.2B-Distilled-Claude-4.6-GGUF

FlameF0X/LFM2.5-1.2B-Distilled-Claude-4.6-GGUF

LFM2.5-1.2B-Distilled-Claude-4.6-GGUF is a machine learning model from FlameF0X. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.

<div align="center" <img src="https://cdn-uploads.huggingface.co/production/uploads/6615494716917dfdc645c44e/IKWKAsS9DFnGoFCmYNQYs.png" alt="Liquid Claude" style="width: 100%; max-width: 100%; height: auto; display: i…

Downloads · 30 days

568

5% of all-time downloads

All-time downloads

10.7K

Public

Repo size

13.1 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.gguf13.1 GB · 100%

At a glance

License: apache-2.0
Access: Public
Created: Apr 9, 2026
Updated: Apr 22, 2026
SHA: 59becce9

Base models

FlameF0X/LFM2.5-1.2B-Distilled-Claude-4.6

Datasets

FlameF0X/Claude-Sonnet-4.6

Model card

From the Hugging Face model README

LFM2.5-1.2B-Distilled-Claude-4.6 (Liquid Claude)

LFM2.5-1.2B-Distilled-Claude-4.6 (Liquid Claude) is a distillation of Claude into LFM2.5-1.2B-Thinking via LoRA.

Training data info:

THINK BLOCK PATTERNS <br> Agentic think blocks (Action/Observation): 8473 <br> Pure reasoning think blocks: 3005

CONSECUTIVE USER MESSAGES <br> Total consecutive user-user pairs: 319

MESSAGE LENGTH STATS (chars)

:)	msgs	avg	max
System	2325	2168	2168
User	11919	332	39134
Assistant	11738	4386	264340

Assistant messages total: 11738 <br> With agentic tool calls in think: 2151 (18.3%)

Total chars in dataset: 60,487,999<br> Approx tokens (~4 chars/token): 15,121,999

Conversations with <=2 messages (system+1): 121<br> Conversations with >5 think blocks in a single assistant msg: 319

Sample chat:

(Ignore the fact that it took 1min to reason, i got a i3-6006u / 12GB as hardware and running the f16 quantization)

Benchmark

The results are in progress.

License: apache-2.0
Languages: en
Created: Apr 9, 2026
Updated: Apr 22, 2026