LLM EXPLORER 67,808 MODELS INDEXED

Qwen3 30B A3B SFT EchoMoE Teacher by McGill-NLP

By McGill-NLP · 422 downloads

Qwen3 30B A3B SFT EchoMoE Teacher is an open-source language model by McGill-NLP. Features: 30b LLM, VRAM: 61.1GB, Context: 32K, License: apache-2.0, Instruction-Based.

  Arxiv:2611.22215 Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-30b-a3b-...   Conversational Dataset:allenai/dolci-instruct...   Echomoe   En   Endpoints compatible   Instruct   Mixture-of-experts   Qwen3 moe   Region:us   Safetensors   Sharded   Tensorflow

Qwen3 30B A3B SFT EchoMoE Teacher Parameters and Internals

LLM NameQwen3 30B A3B SFT EchoMoE Teacher
Repository πŸ€—https://huggingface.co/McGill-NLP/Qwen3-30B-A3B-SFT-EchoMoE-teacher 
Base Model(s)  Qwen3 30B A3B Base   Qwen/Qwen3-30B-A3B-Base
Model Size30b
Required VRAM61.1 GB
Updated2026-11-19
MaintainerMcGill-NLP
Model Typeqwen3_moe
Instruction-BasedYes
Model Files  4.0 GB: 1-of-16   4.0 GB: 2-of-16   4.0 GB: 3-of-16   4.0 GB: 4-of-16   4.0 GB: 5-of-16   4.0 GB: 6-of-16   4.0 GB: 7-of-16   4.0 GB: 8-of-16   4.0 GB: 9-of-16   4.0 GB: 10-of-16   4.0 GB: 11-of-16   4.0 GB: 12-of-16   4.0 GB: 13-of-16   4.0 GB: 14-of-16   4.0 GB: 15-of-16   1.1 GB: 16-of-16
Supported Languagesen
Model ArchitectureQwen3MoeForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version5.3.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Errorsreplace

Best Alternatives to Qwen3 30B A3B SFT EchoMoE Teacher

Best Alternatives
Context / RAM
Downloads
Likes
...LL MASTER CODER M 1million Ctx1024K / 84.8 GB12211
Qwen3 30B A3B YOYO V3986K / 61.1 GB117
...07 YOYO2 TOTAL RECALL Instruct986K / 84.8 GB271
...07 YOYO2 TOTAL RECALL Instruct986K / 106 GB200
Qwen3 30B A3B YOYO V2986K / 61.1 GB194
Qwen3 Coder 30B A3B Instruct256K / 61.1 GB17467711168
Qwen3 30B A3B Instruct 2507256K / 61.1 GB1903736824
Qwen3 30B A3B Instruct 2507256K / 61.1 GB393713
...en3 Coder 30B A3B Instruct FP8256K / 31.2 GB1556690191
Lynx Instruct 30B256K / 61.1 GB2232444
Note: green Score (e.g. "73.2") means that the model is better than McGill-NLP/Qwen3-30B-A3B-SFT-EchoMoE-teacher.