LLM EXPLORER 61,060 MODELS INDEXED

LFM2 8B A1B Instruct Quantum IQ1C Qwen3.6 35B A3B DISTILL2 by DavidAU

By DavidAU · 127 downloads
HF Repo ↗ Copy URL

LFM2 8B A1B Instruct Quantum IQ1C Qwen3.6 35B A3B DISTILL2 is an open-source language model by DavidAU. Features: 8b LLM, VRAM: 16.7GB, Context: 125K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.25.

Base model:finetune:liquidai/l... Base model:liquidai/lfm2-8b-a1...   Conversational   Distill   En   Endpoints compatible   Finetuned   Instruct   Lfm2 moe   Mixture of experts   Moe   Region:us   Safetensors   Sharded   Tensorflow   Unsloth
Model Card on HF 🤗: https://huggingface.co/DavidAU/LFM2-8B-A1B-Instruct-Quantum-IQ1C-Qwen3.6-35B-A3B-DISTILL2 

LFM2 8B A1B Instruct Quantum IQ1C Qwen3.6 35B A3B DISTILL2 Parameters and Internals

LLM NameLFM2 8B A1B Instruct Quantum IQ1C Qwen3.6 35B A3B DISTILL2
Repository 🤗https://huggingface.co/DavidAU/LFM2-8B-A1B-Instruct-Quantum-IQ1C-Qwen3.6-35B-A3B-DISTILL2 
Base Model(s)  LFM2 8B A1B   LiquidAI/LFM2-8B-A1B
Model Size8b
Required VRAM16.7 GB
Updated2026-09-13
MaintainerDavidAU
Model Typelfm2_moe
Instruction-BasedYes
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   5.0 GB: 3-of-4   1.7 GB: 4-of-4
Supported Languagesen
Model ArchitectureLfm2MoeForCausalLM
Licenseapache-2.0
Context Length128000
Model Max Length128000
Transformers Version4.57.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|pad|>
Vocabulary Size65536

Best Alternatives to LFM2 8B A1B Instruct Quantum IQ1C Qwen3.6 35B A3B DISTILL2

Best Alternatives
Context / RAM
Downloads
Likes
LFM2.5 8B A1B Opus Distil125K / 16.9 GB21275
Supertron2.1 8B A1B125K / 17 GB966
Tini Cybersec 8B A1B125K / 16.9 GB142
Supertron 2.1 8B A1B125K / 17 GB496
...m IQ1C Qwen3.6 35B A3B DISTILL125K / 16.7 GB720
Tema Q X4 8B125K / 16.7 GB91
Note: green Score (e.g. "73.2") means that the model is better than DavidAU/LFM2-8B-A1B-Instruct-Quantum-IQ1C-Qwen3.6-35B-A3B-DISTILL2.