LLM EXPLORER 56,604 MODELS INDEXED

Qwen3 30B A3B Thinking 2507 Deepseek V3.1 Distill FP32 by BasedBase

By BasedBase · 387 downloads
HF Repo ↗ Copy URL

Qwen3 30B A3B Thinking 2507 Deepseek V3.1 Distill FP32 is an open-source language model by BasedBase. Features: 30b LLM, VRAM: 122.2GB, Context: 256K, License: apache-2.0, LLM Explorer Score: 0.21.

Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-30b-a3b-...   Code-generation   Distillation   Lora   Lora-merged   Mixture-of-experts   Moe   Qwen   Qwen3 moe   Region:us   Safetensors   Sharded   Svd   Tensorflow
Model Card on HF 🤗: https://huggingface.co/BasedBase/Qwen3-30B-A3B-Thinking-2507-Deepseek-v3.1-Distill-FP32 

Qwen3 30B A3B Thinking 2507 Deepseek V3.1 Distill FP32 Parameters and Internals

LLM NameQwen3 30B A3B Thinking 2507 Deepseek V3.1 Distill FP32
Repository 🤗https://huggingface.co/BasedBase/Qwen3-30B-A3B-Thinking-2507-Deepseek-v3.1-Distill-FP32 
Base Model(s)  Qwen3 30B A3B Thinking 2507   Qwen/Qwen3-30B-A3B-Thinking-2507
Model Size30b
Required VRAM122.2 GB
Updated2025-09-29
MaintainerBasedBase
Model Typeqwen3_moe
Model Files  8.0 GB: 1-of-16   8.0 GB: 2-of-16   8.0 GB: 3-of-16   8.0 GB: 4-of-16   8.0 GB: 5-of-16   8.0 GB: 6-of-16   8.0 GB: 7-of-16   8.0 GB: 8-of-16   8.0 GB: 9-of-16   8.0 GB: 10-of-16   8.0 GB: 11-of-16   8.0 GB: 12-of-16   8.0 GB: 13-of-16   8.0 GB: 14-of-16   8.0 GB: 15-of-16   2.2 GB: 16-of-16
Model ArchitectureQwen3MoeForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version4.55.4
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
LoRA ModelYes
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen3 30B A3B Thinking 2507 Deepseek V3.1 Distill FP32

Best Alternatives
Context / RAM
Downloads
Likes
...LL MASTER CODER M 1million Ctx1024K / 84.8 GB668
... 42B A3B Thinking Total Recall986K / 84.8 GB260
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 GB393713
Qwen3 30B A3B Instruct 2507256K / 61.1 GB1903736824
...en3 Coder 30B A3B Instruct FP8256K / 31.2 GB1556690191
Note: green Score (e.g. "73.2") means that the model is better than BasedBase/Qwen3-30B-A3B-Thinking-2507-Deepseek-v3.1-Distill-FP32.