LFM2.5 8B A1B Terminal ToolBench Full SFT 1Epoch is an open-source language model by LLM-OS-Models. Features: 8b LLM, VRAM: 16.9GB, Context: 125K, LLM Explorer Score: 0.33.
Base model:finetune:liquidai/l... Base model:liquidai/lfm2.5-8b-... Conversational En Endpoints compatible Evaluated Ko Lfm2 moe Region:us Safetensors Sft Tb2-lite Terminal Toolbench Vllm
Model Card on HF 🤗: https://huggingface.co/LLM-OS-Models/LFM2.5-8B-A1B-Terminal-ToolBench-Full-SFT-1Epoch
LFM2.5 8B A1B Terminal ToolBench Full SFT 1Epoch Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
LFM2.5 8B A1B Terminal ToolBench Full SFT 1Epoch Parameters and Internals
| LLM Name | LFM2.5 8B A1B Terminal ToolBench Full SFT 1Epoch |
| Repository 🤗 | https://huggingface.co/LLM-OS-Models/LFM2.5-8B-A1B-Terminal-ToolBench-Full-SFT-1Epoch |
| Model Name | LiquidAI/LFM2.5-8B-A1B |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 16.9 GB |
| Updated | 2026-06-24 |
| Maintainer | LLM-OS-Models |
| Model Type | lfm2_moe |
| Model Files | |
| Supported Languages | en ko |
| Model Architecture | Lfm2MoeForCausalLM |
| Context Length | 128000 |
| Model Max Length | 128000 |
| Transformers Version | 5.5.0 |
| Tokenizer Class | TokenizersBackend |
| Padding Token | <|pad|> |
| Vocabulary Size | 128000 |
Best Alternatives to LFM2.5 8B A1B Terminal ToolBench Full SFT 1Epoch
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| LFM2.5 8B A1B | 125K / 16.9 GB | 118326 | 541 |
| LFM2 8B A1B | 125K / 16.7 GB | 48769 | 366 |
| LFM2.5 8B A1B | 125K / 16.9 GB | 467 | 9 |
| LFM2.5 8B A1B NVFP4 | 125K / 6.9 GB | 279 | 3 |
| LFM2.5 Queen 8B A1B | 125K / 16.8 GB | 100 | 1 |
| Tema Q X4 8B | 125K / 16.7 GB | 465 | 1 |
| Supertron 2.1 8B A1B | 125K / 17 GB | 37 | 5 |
| ... Flash Thinking Quantum IQ1C P | 125K / 16.7 GB | 84 | 5 |
| ...m IQ1C Qwen3.6 35B A3B DISTILL | 125K / 16.7 GB | 72 | 0 |
| LFM2.5 8B A1B Base | 125K / 16.9 GB | 0 | 4 |
Note: green Score (e.g. "73.2") means that the model is better than LLM-OS-Models/LFM2.5-8B-A1B-Terminal-ToolBench-Full-SFT-1Epoch .
Rank the LFM2.5 8B A1B Terminal ToolBench Full SFT 1Epoch Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 54493 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a