Qwen3.6-35B-A3B-DFlash
GGUF quantizations of z-lab/Qwen3.6-35B-A3B-DFlash.
Converted to BF16 using convert_hf_to_gguf.py, then quantized using llama-quantize from llama.cpp.
Available quants
| Quant | Bits | Size | Notes |
|---|---|---|---|
| Q4_K_M | 4 | ~235 MB | Average quality |
| Q5_K | 5 | ~280 MB | High quality |
| Q6_K | 6 | ~326 MB | Very high quality |
| Q8_0 | 8 | ~421 MB | Highest quality, near lossless, Recommended |
| BF16 | 16 | ~771 MB | Full precision, reference file |
Usage
Use in conjunction with existing Qwen3.6 Quants, example config if using llama-server:
[Qwen3.6-35B-A3B-Q8_0-DFlash]
model = /mnt/gguf/Qwen3.6-35B-A3B/Qwen3.6-35B-A3B-Q8_0.gguf
model-draft = /mnt/gguf/Qwen3.6-35B-A3B/Qwen3.6-35B-A3B-DFlash-Q8_0.gguf
spec-type = draft-dflash
spec-draft-n-max = 6
Original model
See the original model card for details on capabilities, benchmarks, and license.