What are the hardware requirements for Lfm2.5 2.6B Thinkingcap Distiller?

Lfm2.5 2.6B Thinkingcap Distiller requires approximately 1.7 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Lfm2.5 2.6B Thinkingcap Distiller and how large is it?

Lfm2.5 2.6B Thinkingcap Distiller is developed by osk-arr00, a model with 26b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Lfm2.5 2.6B Thinkingcap Distiller?

Lfm2.5 2.6B Thinkingcap Distiller is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Lfm2.5 2.6B Thinkingcap Distiller by osk-arr00 — VRAM 1.7GB, 128K context

Name: Lfm2.5 2.6B Thinkingcap Distiller
Author: osk-arr00

Lfm2.5 2.6B Thinkingcap Distiller is an open-source language model by osk-arr00. Features: 26b LLM, VRAM: 1.7GB, Context: 128K, License: apache-2.0, Quantized, LLM Explorer Score: 0.33.

Base model:liquidai/lfm2.5-2.6... Base model:quantized:liquidai/... Chain-of-thought Condensed-thinking Conversational Dataset-generation Dataset:osk-arr00/thinkingcap-... Dataset:r0b0tlab/qwen3.8-max-g... Distillation En Endpoints compatible Es Gguf Lfm Lfm2 Llama-cpp Q4 Quantized Reasoning Region:us Safetensors Self-distillation Thinking-cap Trace-translation

Model Card on HF 🤗: https://huggingface.co/osk-arr00/lfm2.5-2.6B-thinkingcap-distiller

Lfm2.5 2.6B Thinkingcap Distiller Parameters and Internals

LLM Name	Lfm2.5 2.6B Thinkingcap Distiller
Repository 🤗	https://huggingface.co/osk-arr00/lfm2.5-2.6B-thinkingcap-distiller
Base Model(s)	LiquidAI/LFM2.5-2.6B LiquidAI/LFM2.5-2.6B
Model Size	26b
Required VRAM	1.7 GB
Updated	2026-08-13
Maintainer	osk-arr00
Model Type	lfm2
Model Files	1.7 GB 2.9 GB 5.4 GB
Supported Languages	en es
GGUF Quantization	Yes
Quantization Type	q4\|gguf\|q4_k
Model Architecture	Lfm2ForCausalLM
License	apache-2.0
Context Length	131072
Model Max Length	131072
Transformers Version	5.5.0
Tokenizer Class	TokenizersBackend
Padding Token	<\|pad\|>
Vocabulary Size	128000

Rank the Lfm2.5 2.6B Thinkingcap Distiller capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation