Qwen3-Omni-30B-A3B-Instruct GGUF
GGUF weights for Qwen3-Omni-30B-A3B-Instruct in f16, q8_0, and q4_0 quantizations.
| Quantization | Total Size |
|---|---|
| f16 | 64.7 GB |
| q8_0 | 35.4 GB |
| q4_0 | 19.7 GB |
The reference/ directory contains test fixtures for ./test-e2e.sh.
- Downloads last month
- 1,069
Hardware compatibility
Log In to add your hardware
4-bit
8-bit
16-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for DeepMentor/qwen3-omni-30B-a3b-instruct-gguf
Base model
Qwen/Qwen3-Omni-30B-A3B-Instruct