LLM EXPLORER 68,069 MODELS INDEXED

LFM2.5 1.2B Instruct Thinking Claude High Reasoning by DavidAU

By DavidAU · 125 downloads

LFM2.5 1.2B Instruct Thinking Claude High Reasoning is an open-source language model by DavidAU. Features: 1.2b LLM, VRAM: 2.3GB, Context: 125K, Instruction-Based, LLM Explorer Score: 0.21.

  All genres Base model:finetune:liquidai/l... Base model:liquidai/lfm2.5-1.2...   Bfloat16   Context 128k   Conversational   Creative   Creative writing Dataset:teichai/claude-4.5-opu...   Endpoints compatible   Fiction   Fiction story   Fiction writing   Finetuned   Horror   Instruct   Lfm2   Plot generation   Reasoning   Region:us   Roleplaying   Romance   Safetensors   Scene continue   Science fiction   Story   Story generation   Storytelling   Sub-plot generation   Swearing   Thinking   Unsloth   Vivid prose   Vivid writing   Writing

LFM2.5 1.2B Instruct Thinking Claude High Reasoning Parameters and Internals

LLM NameLFM2.5 1.2B Instruct Thinking Claude High Reasoning
Repository πŸ€—https://huggingface.co/DavidAU/LFM2.5-1.2B-Instruct-Thinking-Claude-High-Reasoning 
Base Model(s)  LiquidAI/LFM2.5-1.2B-Instruct   LiquidAI/LFM2.5-1.2B-Instruct
Model Size1.2b
Required VRAM2.3 GB
Updated2026-10-15
MaintainerDavidAU
Model Typelfm2
Instruction-BasedYes
Model Files  2.3 GB
Model ArchitectureLfm2ForCausalLM
Context Length128000
Model Max Length128000
Transformers Version5.0.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|pad|>
Vocabulary Size65536

Best Alternatives to LFM2.5 1.2B Instruct Thinking Claude High Reasoning

Best Alternatives
Context / RAM
Downloads
Likes
LFM2.5 1.2B Instruct125K / 2.3 GB575331647
...M2.5 1.2B Instruct WSP JSONFix125K / 2.3 GB3071
KV1 1.2B125K / 2.3 GB465
Tanpo Marketing125K / 2.3 GB11332
Tanpo Product125K / 2.3 GB9821
...edMCQ LFM2.5 1.2B Answer EN SV125K / 2.3 GB4431
...weMedMCQ LFM2.5 1.2B Answer SV125K / 2.3 GB4421
...weMedMCQ LFM2.5 1.2B Answer EN125K / 2.3 GB4411
...MedMCQ LFM2.5 1.2B Trace SV RW125K / 2.3 GB4381
...MedMCQ LFM2.5 1.2B Trace EN SV125K / 2.3 GB4381
Note: green Score (e.g. "73.2") means that the model is better than DavidAU/LFM2.5-1.2B-Instruct-Thinking-Claude-High-Reasoning.