Documentation Navigation
Models & pricing / Models / LFM2.5-2.6B-GGUF
LFM2.5-2.6B-GGUF Overview
This model's data has not been fully verified and benchmarks may be missing.
LFM2.5-2.6B-GGUF is a chat-reasoning AI model created by LiquidAI, featuring undisclosed parameters and a context window of unknown.
A C/C++ implementation of LLM inference with minimal setup and state-of-the-art performance, supporting various hardware and quantization methods, built on top of the ggml library.
Model Lineage & Specification
lfm25-26b-gguf is LiquidAI's primary release in the current family.
lfm25-26b-ggufComparable models
| Feature | LFM2.5-2.6B-GGUF | Solar Pro 4 | Qwen3.8 Max Preview | Nemotron 3 Ultra |
|---|---|---|---|---|
| Description | A C/C++ implementation of LLM inference with minimal setup and state-of-the-art ... | Solar Pro 4 is a large language model from Upstage built for enterprise workflow... | Preview Qwen flagship for million-token multimodal reasoning and long-horizon ag... | NVIDIA Nemotron 3 Ultra is a flagship open-weight frontier LLM family engineered... |
| API Identifier | lfm25-26b-gguf | upstage-solar-pro-4 | alibaba-qwen3.8-max-preview | nvidia-nemotron-3-ultra |
| Parameters | — | — | — | 550B total / 55B active |
| Context Window | unknown | 524288 | 1M tokens | 1M tokens |
| License / Type | open weights | api only | api only | open weights |
LFM2.5-2.6B-GGUF
A C/C++ implementation of LLM inference with minimal setup and state-of-the-art ...
lfm25-26b-ggufSolar Pro 4
Solar Pro 4 is a large language model from Upstage built for enterprise workflow...
upstage-solar-pro-4Qwen3.8 Max Preview
Preview Qwen flagship for million-token multimodal reasoning and long-horizon ag...
alibaba-qwen3.8-max-previewNemotron 3 Ultra
NVIDIA Nemotron 3 Ultra is a flagship open-weight frontier LLM family engineered...
nvidia-nemotron-3-ultraA C/C++ implementation of LLM inference with minimal setup and state-of-the-art performance, supporting various hardware and quantization methods, built on top of the ggml library.