LLM EXPLORER 60,783 MODELS INDEXED

Darwin 36B Opus by FINAL-Bench

By FINAL-Bench · 400 downloads
HF Repo ↗ Copy URL

Darwin 36B Opus is an open-source language model by FINAL-Bench. Features: 34.7b LLM, VRAM: 69GB, Context: 256K, License: apache-2.0, MoE, LLM Explorer Score: 0.27.

  Arxiv:2605.14386   Advanced-reasoning   Apache-2.0   Ar   Benchmark   Chain-of-thought   Claude-opus   Conversational   Darwin   Darwin-v7   De   Distillation   En   Endpoints compatible   Es   Eval-results   Evolutionary-merge   Fr   Gpqa   Hybrid-vigor   Ja   Ko   Mixture-of-experts   Model-index   Moe   Multilingual   Open-source   Proto-agi   Qwen   Qwen3.6   Qwen3 5 moe text   Reasoning   Region:us   Ru   Safetensors   Sharded   Tensorflow   Thinking   Vidraft   Zh
Model Card on HF 🤗: https://huggingface.co/FINAL-Bench/Darwin-36B-Opus 

Darwin 36B Opus Parameters and Internals

LLM NameDarwin 36B Opus
Repository 🤗https://huggingface.co/FINAL-Bench/Darwin-36B-Opus 
Base Model(s)  Qwen/Qwen3.6-35B-A3B   hesamation/Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled   Qwen/Qwen3.6-35B-A3B   hesamation/Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled
Model Size34.7b
Required VRAM69 GB
Updated2026-07-22
MaintainerFINAL-Bench
Model Typeqwen3_5_moe_text
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   1.1 GB: 21-of-21
Supported Languagesen zh ko ja de fr es ru ar
Model ArchitectureQwen3_5MoeForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version5.5.4
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Vocabulary Size248320
Errorsreplace

Best Alternatives to Darwin 36B Opus

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 35B A3B Abliterated V4256K / 69.3 GB9489208
SIQ 1 35B256K / 69.3 GB671102
Qwen35B Agent R2256K / 69.3 GB28616
Grug 35B A3B256K / 69 GB125231
Qwen35B Agent R2 Abliterated256K / 69.3 GB15640
...A3B W8a8 Llmcompressor V0.12.0256K / 19.4 GB5411
Ornith 1.5 35B A3B Abliterated256K / 69.3 GB2111
Aurora Code 1256K / 69 GB4435
Ornstein3.6 35B A3B256K / 69.3 GB9028
...5B A3B Turkish Financial Model256K / 69.5 GB18324
Note: green Score (e.g. "73.2") means that the model is better than FINAL-Bench/Darwin-36B-Opus.