YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Qwen3 Merged GGUF
Available Files
- qwen3_model_q8_0.gguf - 8-bit quantized (34.8GB) ✅
- qwen3_model_q6_k.gguf - 6-bit quantized (26.9GB) - uploading
- qwen3_model_f16.gguf.aa, .ab, .ac - F16 split into parts (65.5GB total) - uploading
Reassembling the F16 model
The F16 model was split due to file size limits (50GB max per file). To reassemble after downloading all parts:
cat qwen3_model_f16.gguf.* > qwen3_model_f16.gguf
Usage
Compatible with llama.cpp, LM Studio, and other GGUF-supporting inference engines.
- Downloads last month
- 16
Hardware compatibility
Log In to add your hardware
6-bit
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support