LLM EXPLORER 65,040 MODELS INDEXED

LFM2.5 THINKING FINETUNE V6 by WhiteCodex

By WhiteCodex · 17 downloads
HF Repo ↗ Copy URL

LFM2.5 THINKING FINETUNE V6 is an open-source language model by WhiteCodex. Features: 1.2b LLM, VRAM: 2.3GB, Context: 125K, License: apache-2.0, Fine-Tuned, LLM Explorer Score: 0.23.

Base model:finetune:whitecodex... Base model:whitecodex/lfm2.5-t...   Conversational   En   Endpoints compatible   Finetuned   Lfm2   Region:us   Safetensors   Unsloth
Model Card on HF 🤗: https://huggingface.co/WhiteCodex/LFM2.5-THINKING-FINETUNE-V6 

LFM2.5 THINKING FINETUNE V6 Parameters and Internals

LLM NameLFM2.5 THINKING FINETUNE V6
Repository 🤗https://huggingface.co/WhiteCodex/LFM2.5-THINKING-FINETUNE-V6 
Model NameWhiteCodex/LFM2.5-THINKING-FINETUNE-V5
Base Model(s)  WhiteCodex/LFM2.5-THINKING-FINETUNE-V5   WhiteCodex/LFM2.5-THINKING-FINETUNE-V5
Model Size1.2b
Required VRAM2.3 GB
Updated2026-08-05
MaintainerWhiteCodex
Model Typelfm2
Model Files  2.3 GB
Supported Languagesen
Model ArchitectureLfm2ForCausalLM
Licenseapache-2.0
Context Length128000
Model Max Length128000
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|pad|>
Vocabulary Size65536
Torch Data Typefloat16

Best Alternatives to LFM2.5 THINKING FINETUNE V6

Best Alternatives
Context / RAM
Downloads
Likes
LFM2.5 1.2B Instruct125K / 2.3 GB575331647
LFM2.5 1.2B JP 202606125K / 2.3 GB2400669
LFM2.5 1.2B Thinking125K / 2.3 GB32455354
...edMCQ LFM2.5 1.2B Answer EN SV125K / 2.3 GB4341
...weMedMCQ LFM2.5 1.2B Answer SV125K / 2.3 GB4331
...weMedMCQ LFM2.5 1.2B Answer EN125K / 2.3 GB4321
...MedMCQ LFM2.5 1.2B Trace SV RW125K / 2.3 GB4291
...MedMCQ LFM2.5 1.2B Trace EN SV125K / 2.3 GB4291
SweMedMCQ LFM2.5 1.2B Trace SV125K / 2.3 GB4251
SweMedMCQ LFM2.5 1.2B Trace EN125K / 2.3 GB4221
Note: green Score (e.g. "73.2") means that the model is better than WhiteCodex/LFM2.5-THINKING-FINETUNE-V6.