What are the hardware requirements for Fabric1.6?

Fabric1.6 requires approximately 72.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Fabric1.6 and how large is it?

Fabric1.6 is developed by FabricAI, 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 Fabric1.6?

Fabric1.6 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Fabric1.6 by FabricAI — VRAM 72.2GB

Name: Fabric1.6
Author: FabricAI

Fabric1.6 is an open-source language model by FabricAI. Features: 35b LLM, VRAM: 72.2GB, License: apache-2.0, LLM Explorer Score: 0.25.

Agentic Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-35b-a3... Bf16 Conversational Dataset:fabricai/maple Dataset:huggingfacetb/smoltalk... Dataset:nousresearch/hermes-fu... Dataset:open-r1/openr1-math-22... Dataset:open-thoughts/openthou... Dataset:openassistant/oasst2 Endpoints compatible Fabric1.6 Hybrid-attention Image-text-to-text Long-context Mixture-of-experts Model-index Multimodal Pytorch Qwen3 5 moe Reasoning Region:us Safetensors Sharded Tensorflow Tool-calling Video Video-text-to-text Vision

Model Card on HF 🤗: https://huggingface.co/FabricAI/Fabric1.6

Fabric1.6 Parameters and Internals

LLM Name	Fabric1.6
Repository 🤗	https://huggingface.co/FabricAI/Fabric1.6
Base Model(s)	Qwen/Qwen3.5-35B-A3B-Base Qwen/Qwen3.5-35B-A3B-Base
Model Size	35b
Required VRAM	72.2 GB
Updated	2026-08-11
Maintainer	FabricAI
Model Type	qwen3_5_moe
Model Files	4.0 GB: 1-of-26 1.3 GB: 2-of-26 3.4 GB: 3-of-26 3.4 GB: 4-of-26 3.4 GB: 5-of-26 4.0 GB: 6-of-26 1.1 GB: 7-of-26 4.0 GB: 8-of-26 1.1 GB: 9-of-26 4.0 GB: 10-of-26 1.1 GB: 11-of-26 3.4 GB: 12-of-26 1.6 GB: 13-of-26 3.4 GB: 14-of-26 1.6 GB: 15-of-26 4.0 GB: 16-of-26 1.1 GB: 17-of-26 4.0 GB: 18-of-26 1.1 GB: 19-of-26 3.4 GB: 20-of-26 1.6 GB: 21-of-26 3.4 GB: 22-of-26 3.4 GB: 23-of-26 3.4 GB: 24-of-26 3.8 GB: 25-of-26 2.2 GB: 26-of-26
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	4.57.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Fabric1.6 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 Fabric1.6

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.6 35B A3B	0K / 72.2 GB	5540855	2648
Qwen3.5 35B A3B	0K / 72.3 GB	2158511	1482
Ornith 1.0 35B	0K / 70.4 GB	2741264	484
KAT Coder V2.5 Dev	0K / 69.7 GB	17885	537
Qwen3.6 35B A3B NVFP4	0K / 23.4 GB	8788684	482
Qwen AgentWorld 35B A3B	0K / 69.2 GB	66155	665
Qwen3.6 35B A3B FP8	0K / 0.8 GB	8984811	343
XYZ Aquila Mini	0K / 70.2 GB	1760	432
Qwen3.6 35B A3B NVFP4 Fast	0K / 23.6 GB	463661	98
Qwen3.6 35B A3B Escha W2	0K / 12.3 GB	3622	236

Note: green Score (e.g. "73.2") means that the model is better than FabricAI/Fabric1.6.