What are the hardware requirements for Qwen3.6 35B A3B GPTQ Int4?

Qwen3.6 35B A3B GPTQ Int4 requires approximately 22.7 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3.6 35B A3B GPTQ Int4 and how large is it?

Qwen3.6 35B A3B GPTQ Int4 is developed by palmfuture, a model with 35b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Qwen3.6 35B A3B GPTQ Int4 perform on standard benchmarks?

Qwen3.6 35B A3B GPTQ Int4 has the following published scores: LMSYS ELO 1395. Compare against reference models on this page or on the LLM Explorer leaderboards.

Qwen3.6 35B A3B GPTQ Int4 by palmfuture — VRAM 22.7GB

Name: Qwen3.6 35B A3B GPTQ Int4
Author: palmfuture

Qwen3.6 35B A3B GPTQ Int4 is an open-source language model by palmfuture. Features: 35b LLM, VRAM: 22.7GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.48, ELO: 1395.

4-bit Base model:quantized:qwen/qwen... Base model:qwen/qwen3.6-35b-a3... Conversational En Endpoints compatible Gptq Image-text-to-text Int4 Moe Mtp Multilingual Quantized Qwen3.6 Qwen3 5 moe Region:us Safetensors Sharded Speculative-decoding Tensorflow Th Zh

Model Card on HF 🤗: https://huggingface.co/palmfuture/Qwen3.6-35B-A3B-GPTQ-Int4

Qwen3.6 35B A3B GPTQ Int4 Benchmarks

LMSys ELO 1395 vs 1272 (so35) 9.7%

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Qwen3.6 35B A3B GPTQ Int4 Parameters and Internals

LLM Name	Qwen3.6 35B A3B GPTQ Int4
Repository 🤗	https://huggingface.co/palmfuture/Qwen3.6-35B-A3B-GPTQ-Int4
Base Model(s)	Qwen/Qwen3.6-35B-A3B Qwen/Qwen3.6-35B-A3B
Model Size	35b
Required VRAM	22.7 GB
Updated	2026-08-09
Maintainer	palmfuture
Model Type	qwen3_5_moe
Model Files	4.3 GB: 1-of-6 4.3 GB: 2-of-6 4.3 GB: 3-of-6 4.3 GB: 4-of-6 4.3 GB: 5-of-6 1.2 GB: 6-of-6 1.7 GB
Supported Languages	en th zh
GPTQ Quantization	Yes
Quantization Type	gptq
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	5.5.4
Tokenizer Class	Qwen2TokenizerFast
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Qwen3.6 35B A3B GPTQ Int4 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 Qwen3.6 35B A3B GPTQ Int4

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.5 35B A3B GPTQ Int4	0K / 24.3 GB	453653	92
Qwen3.5 35B A3B GPTQ Int4	0K / 21.7 GB	31	4
Qwen3.6 35B A3B MLX 4bit	0K / 20.5 GB	513193	6
Qwen3.6 35B A3B MLX 6bit	0K / 28.9 GB	478592	2
Qwen3.6 35B A3B 6bit	0K / 28.9 GB	2742	8
Qwen3.6 35B A3B 5bit	0K / 24.7 GB	1628	5
Qwen3.6 35B A3B 4bit	0K / 20.5 GB	62036	92
Qwen3.6 35B A3B 8bit	0K / 37.8 GB	120175	27
Ornith 1.0 35B 4bit	0K / 20.5 GB	6835	13
Qwen3.6 35B A3B OptiQ 4bit	0K / 22.1 GB	14730	44

Note: green Score (e.g. "73.2") means that the model is better than palmfuture/Qwen3.6-35B-A3B-GPTQ-Int4.