What are the hardware requirements for Qwen3.5 35B A3B MXFP8 CT RTN AutoRound?

Qwen3.5 35B A3B MXFP8 CT RTN AutoRound requires approximately 38.9 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3.5 35B A3B MXFP8 CT RTN AutoRound and how large is it?

Qwen3.5 35B A3B MXFP8 CT RTN AutoRound is developed by INCModel3, 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 Qwen3.5 35B A3B MXFP8 CT RTN AutoRound?

Qwen3.5 35B A3B MXFP8 CT RTN AutoRound is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen3.5 35B A3B MXFP8 CT RTN AutoRound by INCModel3 — VRAM 38.9GB

Name: Qwen3.5 35B A3B MXFP8 CT RTN AutoRound
Author: INCModel3

Qwen3.5 35B A3B MXFP8 CT RTN AutoRound is an open-source language model by INCModel3. Features: 35b LLM, VRAM: 38.9GB, LLM Explorer Score: 0.3.

Autoquant-agent Autoround Base model:quantized:qwen/qwen... Base model:qwen/qwen3.5-35b-a3... Compressed-tensors Conversational Mxfp8 Quantized Qwen3 5 moe Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/INCModel3/Qwen3.5-35B-A3B-MXFP8-CT-RTN-AutoRound

Qwen3.5 35B A3B MXFP8 CT RTN AutoRound Parameters and Internals

LLM Name	Qwen3.5 35B A3B MXFP8 CT RTN AutoRound
Repository 🤗	https://huggingface.co/INCModel3/Qwen3.5-35B-A3B-MXFP8-CT-RTN-AutoRound
Base Model(s)	Qwen/Qwen3.5-35B-A3B Qwen/Qwen3.5-35B-A3B
Model Size	35b
Required VRAM	38.9 GB
Updated	2026-09-18
Maintainer	INCModel3
Model Type	qwen3_5_moe
Model Files	2.8 GB: 1-of-14 2.8 GB: 2-of-14 2.8 GB: 3-of-14 2.8 GB: 4-of-14 2.8 GB: 5-of-14 2.8 GB: 6-of-14 2.8 GB: 7-of-14 2.8 GB: 8-of-14 3.7 GB: 9-of-14 2.8 GB: 10-of-14 2.8 GB: 11-of-14 2.8 GB: 12-of-14 3.1 GB: 13-of-14 1.3 GB: 14-of-14
Model Architecture	Qwen3_5MoeForConditionalGeneration
Model Max Length	262144
Transformers Version	4.57.0.dev0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Qwen3.5 35B A3B MXFP8 CT RTN AutoRound 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 Qwen3.5 35B A3B MXFP8 CT RTN AutoRound

Best Alternatives	Context / RAM	Downloads	Likes
Ornith 1.5 35B A3B NPU2	256K / GB	225	1
Qwen3.6 35B A3B	0K / 72.2 GB	5540855	2648
Qwen3.5 35B A3B	0K / 72.3 GB	2158511	1482
Qwen3.6 35B A3B NVFP4	0K / 23.4 GB	8788684	482
Ornith 1.0 35B	0K / 70.4 GB	2047127	506
Qwen3.6 35B A3B FP8	0K / 0.8 GB	8984811	343
KAT Coder V2.5 Dev	0K / 69.7 GB	17885	537
Qwen AgentWorld 35B A3B	0K / 69.2 GB	66155	665
Qwen3.6 35B A3B NVFP4 Fast	0K / 23.6 GB	463661	98
Qwen3.5 35B A3B	0K / 72.3 GB	2210	16

Note: green Score (e.g. "73.2") means that the model is better than INCModel3/Qwen3.5-35B-A3B-MXFP8-CT-RTN-AutoRound.