What are the hardware requirements for DAOS Fusion?

DAOS Fusion requires approximately 69.3 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 DAOS Fusion and how large is it?

DAOS Fusion is developed by OliviaRossi, a model with 35b 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 DAOS Fusion?

DAOS Fusion is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

DAOS Fusion by OliviaRossi — VRAM 69.3GB, 256K context

Name: DAOS Fusion
Author: OliviaRossi

DAOS Fusion is an open-source language model by OliviaRossi. Features: 35b LLM, VRAM: 69.3GB, Context: 256K, License: apache-2.0, Code Generating, LLM Explorer Score: 0.31.

Agent Base model:jackrong/qwopus3.6-... Base model:kwaipilot/kat-coder... Base model:merge:jackrong/qwop... Base model:merge:kwaipilot/kat... Base model:merge:ornith-ai/orn... Base model:merge:qwen/qwen-age... Base model:ornith-ai/ornith-1.... Base model:qwen/qwen-agentworl... Code Codegen Conversational Daos-fusion Dare Della Delta-net En Endpoints compatible Llama.cpp Merge Model-stock Moe Qwen3.5 Qwen3.6 Qwen3 5 moe Reasoning Region:us Safetensors Sharded Star Tensorflow Vllm Zh

Model Card on HF 🤗: https://huggingface.co/OliviaRossi/DAOS-Fusion

DAOS Fusion Parameters and Internals

LLM Name	DAOS Fusion
Repository 🤗	https://huggingface.co/OliviaRossi/DAOS-Fusion
Base Model(s)	Qwen AgentWorld 35B A3B Kwaipilot/KAT-Coder-V2.5-Dev Jackrong/Qwopus3.6-35B-A3B-Coder ornith-ai/Ornith-1.5-35B-A3B Qwen/Qwen-AgentWorld-35B-A3B Kwaipilot/KAT-Coder-V2.5-Dev Jackrong/Qwopus3.6-35B-A3B-Coder ornith-ai/Ornith-1.5-35B-A3B
Model Size	35b
Required VRAM	69.3 GB
Updated	2026-09-03
Maintainer	OliviaRossi
Model Type	qwen3_5_moe
Model Files	4.3 GB: 1-of-17 4.5 GB: 2-of-17 3.9 GB: 3-of-17 4.5 GB: 4-of-17 3.8 GB: 5-of-17 4.6 GB: 6-of-17 3.8 GB: 7-of-17 4.6 GB: 8-of-17 3.9 GB: 9-of-17 4.5 GB: 10-of-17 3.9 GB: 11-of-17 4.5 GB: 12-of-17 4.0 GB: 13-of-17 4.5 GB: 14-of-17 3.9 GB: 15-of-17 4.5 GB: 16-of-17 1.6 GB: 17-of-17
Supported Languages	en zh code
Generates Code	Yes
Model Architecture	Qwen3_5MoeForCausalLM
License	apache-2.0
Context Length	262144
Model Max Length	262144
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	248320
Errors	replace

Rank the DAOS Fusion 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 DAOS Fusion

Best Alternatives	Context / RAM	Downloads	Likes
UltiMerge	256K / 69.3 GB	557	2

Note: green Score (e.g. "73.2") means that the model is better than OliviaRossi/DAOS-Fusion.