LLM EXPLORER 64,811 MODELS INDEXED

AgentMercury Qwen3.5 35B A3B by Minbyul

By Minbyul · 18 downloads
HF Repo ↗ Copy URL

AgentMercury Qwen3.5 35B A3B is an open-source language model by Minbyul. Features: 35b LLM, VRAM: 69.7GB, License: apache-2.0, LLM Explorer Score: 0.25.

  Agent Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-35b-a3...   Conversational   En   Endpoints compatible   Grpo   Image-text-to-text   Mcp   Moe   Qwen3 5   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow   Tool-use
Model Card on HF 🤗: https://huggingface.co/Minbyul/AgentMercury-Qwen3.5-35B-A3B 

AgentMercury Qwen3.5 35B A3B Parameters and Internals

LLM NameAgentMercury Qwen3.5 35B A3B
Repository 🤗https://huggingface.co/Minbyul/AgentMercury-Qwen3.5-35B-A3B 
Base Model(s)  Qwen/Qwen3.5-35B-A3B   Qwen/Qwen3.5-35B-A3B
Model Size35b
Required VRAM69.7 GB
Updated2026-08-19
MaintainerMinbyul
Model Typeqwen3_5_moe
Model Files  5.4 GB: 0-of-13   5.4 GB: 1-of-13   5.4 GB: 2-of-13   5.4 GB: 3-of-13   5.4 GB: 4-of-13   5.4 GB: 5-of-13   5.4 GB: 6-of-13   5.4 GB: 7-of-13   5.4 GB: 8-of-13   5.4 GB: 9-of-13   5.4 GB: 10-of-13   5.4 GB: 11-of-13   4.9 GB: 12-of-13
Supported Languagesen
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to AgentMercury Qwen3.5 35B A3B

Best Alternatives
Context / RAM
Downloads
Likes
....5 35B A3B Sceptic V3 1M W4A161024K / 26.1 GB2230
...AgentWorld 35B A3B Abliterated256K / 69.2 GB96218
Ornith 1.5 35B A3B NPU2256K /  GB710
Qwen3.6 35B A3B NPU2256K /  GB850
Qwen3.6 35B A3B0K / 72.2 GB55408552648
Qwen3.5 35B A3B0K / 72.3 GB21585111482
Qwen3.6 35B A3B NVFP40K / 23.4 GB8788684482
Ornith 1.0 35B0K / 70.4 GB1369192516
Qwen3.6 35B A3B FP80K / 0.8 GB8984811343
Qwen AgentWorld 35B A3B0K / 69.2 GB66155665
Note: green Score (e.g. "73.2") means that the model is better than Minbyul/AgentMercury-Qwen3.5-35B-A3B.