L

LFM2.5 2.6B GGUF

Open weights
Open LLM LiquidAI Docs ↗
Model spec
Provider
LiquidAI
Context window
-
Max output
-
Input price
-
Output price
-
License
See model card
Open weights
Yes

LFM2.5 2.6B GGUF is a modestly-sized open-weight language model distributed in GGUF format by LiquidAI, targeting developers who prioritize model transparency and local execution. With undisclosed context handling but clear open-weights licensing, it occupies a niche between proprietary small LLMs and fully closed alternatives. Developers seeking a hackable, locally-runnable text model for lightweight applications or experimentation—particularly those already using GGUF tooling—should evaluate this option, while those requiring documented performance characteristics or commercial support may need alternatives.

Modality

Text

Use cases

Local text generation with small-scale LLM applicationsExperimentation with open-weight models in resource-constrained environmentsFine-tuning for specialized text tasks (given its open weights)Educational or prototyping use cases involving GGUF-format modelsIntegration into lightweight AI pipelines where proprietary models are unsuitable

Pros & cons

Pros

  • Open-weight design allows modification and transparency
  • GGUF format enables efficient CPU/GPU inference with tools like llama.cpp
  • Smaller size (2.6B) may lower hardware requirements compared to larger LLMs
  • Hosted on Hugging Face for community access

Cons

  • Key specifications (context window, output limits) are undocumented
  • Lack of commercial pricing info suggests limited enterprise support
  • Smaller scale may limit complex reasoning capabilities
  • No multimodal support (text-only)

Related models

J

Jamba 1.5 Large

Open weights
Open LLM

256K ctx · $2/$8 per 1M · AI21 Labs

Jamba 1.5 Large is AI21 Labs' hybrid Mamba-Transformer open LLM with a 256k token context window, designed for text-base...

View details → Visit
D

DeepSeek-V3

Open weights
Open LLM

128K ctx · $0.27/$1.10 per 1M · DeepSeek

DeepSeek-V3 is a large open-weight mixture-of-experts model developed by DeepSeek, offering high-quality performance at ...

View details → Visit
L

Llama 3.1 405B

Open weights
Open LLM

128K ctx · Meta

Llama 3.1 405B is Meta's largest open-weight language model, designed to compete with leading closed frontier models acr...

View details → Visit
L

Llama 3.1 70B

Open weights
Open LLM

128K ctx · Meta

Llama 3.1 70B is an open-weight large language model designed for self-hosting, offering a balance between capability an...

View details → Visit
Q

Qwen2.5 72B

Open weights
Open LLM

128K ctx · Alibaba

Qwen2.5 72B is Alibaba's open-weight large language model designed for multilingual, math, and coding tasks. It features...

View details → Visit
B

Bonsai 27B mlx 1bit

Open weights
Open LLM

prism-ml

Bonsai 27B mlx 1bit is an open-weight large language model developed by prism-ml and available on Hugging Face. It is de...

View details → Visit

Compare LFM2.5 2.6B GGUF

All comparisons →

Read the official docs

LFM2.5 2.6B GGUF

View documentation