Downloads · 30 days
31
12% of all-time downloads
qwen3next-80b-a3b-2p02bit-r32_v7
minjaechoi/qwen3next-80b-a3b-2p02bit-r32_v7
qwen3next-80b-a3b-2p02bit-r32_v7 is a text generation model from minjaechoi. Use it when you need the model to write or continue text. It is set up for transformers.
Internal research checkpoint. Routed experts average 2.016 bits; every other weight is BF16. Weights are stored dequantized in BF16 tensors and load with stock transformers / vLLM.
All-time downloads
253
Public
Parameters
81.3B
163 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors163 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- qwen3_next
- Access
- Public
- Created
- Sep 21, 2026
- Updated
- Sep 21, 2026
- SHA
- 4b45885e
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3-Next-80B-A3B-Thinking — 2.016-bit routed experts (r32_v7)
Internal research checkpoint. Routed experts average 2.016 bits; every other weight is BF16. Weights are stored
dequantized in BF16 tensors and load with stock transformers / vLLM.
| Base model | Qwen/Qwen3-Next-80B-A3B-Thinking |
| Routed-expert average | 2.016 bits |
| Internal ID | r32_v7 |
License follows the base model.
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3_next
- Created
- Sep 21, 2026
- Updated
- Sep 21, 2026