What are the hardware requirements for Qwen35B Agent R2?

Qwen35B Agent R2 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 Qwen35B Agent R2 and how large is it?

Qwen35B Agent R2 is developed by hotdogs, a model with 34.7b 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 Qwen35B Agent R2?

Qwen35B Agent R2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen35B Agent R2 by hotdogs — VRAM 69.3GB, 256K context

Name: Qwen35B Agent R2
Author: hotdogs

Qwen35B Agent R2 is an open-source language model by hotdogs. Features: 34.7b LLM, VRAM: 69.3GB, Context: 256K, License: agpl-3.0, MoE, LLM Explorer Score: 0.3.

Agent Agent-world Base model:quantized:qwen/qwen... Base model:qwen/qwen-agentworl... Conversational Dataset:11-47/claude opus 4.8 ... Dataset:cx-cmu/agent trajector... Dataset:hotdogs/uka-fable-reas... En Endpoints compatible Fable Gguf Mixture-of-experts Moe Opus Qwen Qwen3 5 moe text Reasoning Region:us Safetensors Sft Sharded Tensorflow Th Thai Tool-calling Tool-use Ykai

Model Card on HF 🤗: https://huggingface.co/hotdogs/Qwen35B-Agent-R2

Qwen35B Agent R2 Parameters and Internals

LLM Name	Qwen35B Agent R2
Repository 🤗	https://huggingface.co/hotdogs/Qwen35B-Agent-R2
Base Model(s)	Qwen AgentWorld 35B A3B Qwen/Qwen-AgentWorld-35B-A3B
Model Size	34.7b
Required VRAM	69.3 GB
Updated	2026-07-19
Maintainer	hotdogs
Model Type	qwen3_5_moe_text
Model Files	49.7 GB: 1-of-2 19.6 GB: 2-of-2
Supported Languages	en th
Model Architecture	Qwen3_5MoeForCausalLM
License	agpl-3.0
Context Length	262144
Model Max Length	262144
Transformers Version	5.12.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	248320
Errors	replace

Rank the Qwen35B Agent R2 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 Qwen35B Agent R2

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.6 35B A3B Abliterated V4	256K / 69.3 GB	965756	7
SIQ 1 35B	256K / 69.3 GB	799	102
Grug 35B A3B	256K / 69 GB	1252	31
Qwen35B Agent R2 Abliterated	256K / 69.3 GB	1564	0
...A3B W8a8 Llmcompressor V0.12.0	256K / 19.4 GB	541	1
Ornith 1.5 35B A3B Abliterated	256K / 69.3 GB	211	1
Aurora Code 1	256K / 69 GB	443	5
Darwin 36B Opus	256K / 69 GB	400	87
Ornstein3.6 35B A3B	256K / 69.3 GB	902	8
...5B A3B Turkish Financial Model	256K / 69.5 GB	156	24

Note: green Score (e.g. "73.2") means that the model is better than hotdogs/Qwen35B-Agent-R2.