LLM EXPLORER 55,709 MODELS INDEXED

BTL 4 by badtheorylabs

By badtheorylabs · 571 downloads
HF Repo ↗ Copy URL

BTL 4 is an open-source language model by badtheorylabs. Features: 35b LLM, VRAM: 69.9GB, License: apache-2.0, LLM Explorer Score: 0.44.

  Agentic   Code   Conversational   Endpoints compatible   Image-text-to-text   Qwen3 5 moe   Reasoning   Region:us   Safetensors   Sharded   Tensorflow   Tool-use
Model Card on HF 🤗: https://huggingface.co/badtheorylabs/BTL-4 

BTL 4 Parameters and Internals

LLM NameBTL 4
Repository 🤗https://huggingface.co/badtheorylabs/BTL-4 
Model Name/vol/merged/btl4-pilot
Base Model(s)  Ornith-1.0-35B   /Ornith-1.0-35B
Model Size35b
Required VRAM69.9 GB
Updated2026-08-08
Maintainerbadtheorylabs
Model Typeqwen3_5_moe
Model Files  3.8 GB: 1-of-21   3.8 GB: 2-of-21   3.4 GB: 3-of-21   3.3 GB: 4-of-21   3.4 GB: 5-of-21   3.3 GB: 6-of-21   3.4 GB: 7-of-21   3.3 GB: 8-of-21   3.4 GB: 9-of-21   3.3 GB: 10-of-21   3.4 GB: 11-of-21   3.3 GB: 12-of-21   3.4 GB: 13-of-21   3.3 GB: 14-of-21   3.4 GB: 15-of-21   3.3 GB: 16-of-21   3.4 GB: 17-of-21   3.3 GB: 18-of-21   3.4 GB: 19-of-21   3.3 GB: 20-of-21   2.0 GB: 21-of-21
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.13.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to BTL 4

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 35B A3B0K / 72.2 GB55408552648
KAT Coder V2.5 Dev0K / 69.7 GB17885537
Qwen3.6 35B A3B NVFP40K / 23.4 GB8788684482
XYZ Aquila Mini0K / 70.2 GB1760432
Qwen3.6 35B A3B Escha W20K / 12.3 GB3622236
Qwen3.6 35B A3B Abliterated V20K / 70.2 GB6219
BigBang V10K / 71.5 GB15484
...e 4.7 Opus Reasoning Distilled0K / 72.2 GB28687194
GRM 3.2 Sky0K / 70.4 GB71731
Ornith 1.0 35B MTPLX0K / 19.5 GB2503418
Note: green Score (e.g. "73.2") means that the model is better than badtheorylabs/BTL-4.