What are the hardware requirements for Darwin 36B Opus ABLITERATED HERETIC?

Darwin 36B Opus ABLITERATED HERETIC requires approximately 70 GB of VRAM and supports a context window of 256K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Darwin 36B Opus ABLITERATED HERETIC and how large is it?

Darwin 36B Opus ABLITERATED HERETIC is developed by Guilherme34, a model with 34.7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Darwin 36B Opus ABLITERATED HERETIC?

Darwin 36B Opus ABLITERATED HERETIC is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Darwin 36B Opus ABLITERATED HERETIC by Guilherme34 — VRAM 70GB, 256K context

Name: Darwin 36B Opus ABLITERATED HERETIC
Author: Guilherme34

Darwin 36B Opus ABLITERATED HERETIC is an open-source language model by Guilherme34. Features: 34.7b LLM, VRAM: 70GB, Context: 256K, MoE, LLM Explorer Score: 0.23.

Base model:final-bench/darwin-... Base model:finetune:final-benc... Conversational Endpoints compatible Moe Qwen3 5 moe text Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Guilherme34/Darwin-36B-Opus-ABLITERATED-HERETIC

Darwin 36B Opus ABLITERATED HERETIC Parameters and Internals

LLM Name	Darwin 36B Opus ABLITERATED HERETIC
Repository 🤗	https://huggingface.co/Guilherme34/Darwin-36B-Opus-ABLITERATED-HERETIC
Base Model(s)	Darwin 36B Opus FINAL-Bench/Darwin-36B-Opus
Model Size	34.7b
Required VRAM	70 GB
Updated	2026-04-28
Maintainer	Guilherme34
Model Type	qwen3_5_moe_text
Model Files	1.1 GB: 1-of-42 1.7 GB: 2-of-42 1.7 GB: 3-of-42 1.7 GB: 4-of-42 1.7 GB: 5-of-42 1.7 GB: 6-of-42 1.7 GB: 7-of-42 1.7 GB: 8-of-42 1.7 GB: 9-of-42 1.7 GB: 10-of-42 1.7 GB: 11-of-42 1.7 GB: 12-of-42 1.7 GB: 13-of-42 1.7 GB: 14-of-42 1.7 GB: 15-of-42 1.7 GB: 16-of-42 1.7 GB: 17-of-42 1.7 GB: 18-of-42 1.7 GB: 19-of-42 1.7 GB: 20-of-42 1.7 GB: 21-of-42 1.7 GB: 22-of-42 1.7 GB: 23-of-42 1.7 GB: 24-of-42 1.7 GB: 25-of-42 1.7 GB: 26-of-42 1.7 GB: 27-of-42 1.7 GB: 28-of-42 1.7 GB: 29-of-42 1.7 GB: 30-of-42 1.7 GB: 31-of-42 1.7 GB: 32-of-42 1.7 GB: 33-of-42 1.7 GB: 34-of-42 1.7 GB: 35-of-42 1.7 GB: 36-of-42 1.7 GB: 37-of-42 1.7 GB: 38-of-42 1.7 GB: 39-of-42 1.7 GB: 40-of-42 1.6 GB: 41-of-42 1.0 GB: 42-of-42
Model Architecture	Qwen3_5MoeForCausalLM
Context Length	262144
Model Max Length	262144
Transformers Version	5.6.2
Vocabulary Size	248320

Rank the Darwin 36B Opus ABLITERATED HERETIC capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Darwin 36B Opus ABLITERATED HERETIC

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.6 35B A3B Abliterated V4	256K / 69.3 GB	965756	7
SIQ 1 35B	256K / 69.3 GB	799	102
Qwen35B Agent R2	256K / 69.3 GB	2861	6
Grug 35B A3B	256K / 69 GB	1252	31
Qwen35B Agent R2 Abliterated	256K / 69.3 GB	1564	0
...A3B W8a8 Llmcompressor V0.12.0	256K / 19.4 GB	541	1
Ornith 1.5 35B A3B Abliterated	256K / 69.3 GB	211	1
Aurora Code 1	256K / 69 GB	443	5
Darwin 36B Opus	256K / 69 GB	400	87
Ornstein3.6 35B A3B	256K / 69.3 GB	902	8

Note: green Score (e.g. "73.2") means that the model is better than Guilherme34/Darwin-36B-Opus-ABLITERATED-HERETIC.