What are the hardware requirements for Darwin 180B RSI R3 Sushi 2.5bpw?

Darwin 180B RSI R3 Sushi 2.5bpw requires approximately 0.8 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Darwin 180B RSI R3 Sushi 2.5bpw and how large is it?

Darwin 180B RSI R3 Sushi 2.5bpw is developed by Cianidos, a model with 180b 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 180B RSI R3 Sushi 2.5bpw?

Darwin 180B RSI R3 Sushi 2.5bpw is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Darwin 180B RSI R3 Sushi 2.5bpw by Cianidos — VRAM 0.8GB

Name: Darwin 180B RSI R3 Sushi 2.5bpw
Author: Cianidos

Darwin 180B RSI R3 Sushi 2.5bpw is an open-source language model by Cianidos. Features: 180b LLM, VRAM: 0.8GB, License: other, LLM Explorer Score: 0.29.

Arxiv:2605.14386 Arxiv:2609.20269 8-bit Apple-silicon Base model:final-bench/darwin-... Base model:quantized:final-ben... Conversational Darwin Darwin-rsi En Exl3 Image-text-to-text Ja Ko Long-context Mlx Moe Multilingual Quantized Qwen4 exp Reasoning Region:us Safetensors Sushi Vision Vision-language Zh

Model Card on HF 🤗: https://huggingface.co/Cianidos/Darwin-180B-RSI-R3-Sushi-2.5bpw

Darwin 180B RSI R3 Sushi 2.5bpw Parameters and Internals

LLM Name	Darwin 180B RSI R3 Sushi 2.5bpw
Repository 🤗	https://huggingface.co/Cianidos/Darwin-180B-RSI-R3-Sushi-2.5bpw
Base Model(s)	Darwin 180B RSI R3 FINAL-Bench/Darwin-180B-RSI-R3
Model Size	180b
Required VRAM	0.8 GB
Updated	2026-10-30
Maintainer	Cianidos
Model Type	qwen4_exp
Model Files	0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB 0.8 GB
Supported Languages	en ko zh ja
Model Architecture	Qwen4ExpForConditionalGeneration
License	other
Transformers Version	5.8.0.dev0

Rank the Darwin 180B RSI R3 Sushi 2.5bpw 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 180B RSI R3 Sushi 2.5bpw

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.8 Flash Next	0K / 129.5 GB	4810	3918
Qwen3.8 Flash Next OQ4e Mtp	0K / 106.4 GB	21637	86
ThinkingCap Qwen3.8 Flash Next	0K / 127.7 GB	213	33
Darwin 180B RSI	0K / 119 GB	353	94
CYBER FROST 3.8 BF16	0K / 124.3 GB	2263	65
...wen3.8 Flash Next Oq4 Mix6 Mtp	0K / 54.6 GB	761	2
Qwen3.8 Flash Next FP8	0K / 65.7 GB	2219	117
...Qwen3.8 Flash Next Abliterated	0K / 129.5 GB	493	42
...ngCap Qwen3.8 Flash Next NVFP4	0K / 131.5 GB	224	7
Qwen3.8 Flash Next W4A16	0K / 0.5 GB	6043	22

Note: green Score (e.g. "73.2") means that the model is better than Cianidos/Darwin-180B-RSI-R3-Sushi-2.5bpw.