You can deploy this model and start earning money today!

Radamanthys11/
Qwen3.6-27B-DFlash-GGUF

Name: Qwen3.6-27B-DFlash-GGUF
Rating: 2.5 (114 reviews)

z-lab/Qwen3.6-27B-DFlash

quantized

endpoints_compatible

conversational

Views

No views yet

Qwen 3.6 27B DFlash GGUF

GGUF made to use in ikawrakow/ik_llama.cpp, currently for PR #1970. The small quantizations delivered here are made for test purposes; feel free to create your own quantization.

Derived from the safetensors DFlash draft model z-lab/Qwen3.6-27B-DFlash.

Compatible target model

Qwen3.6-27B.gguf - Mainly tested with Q8_0.

Files

File	Quant	Size
`qwen36-27b-dflash-F16.gguf`	F16	3.3 GB
`qwen36-27b-dflash-Q8_0.gguf`	Q8_0	1.8 GB
`qwen36-27b-dflash-Q4_K_M.gguf`	Q4_K_M	986 MB

Usage

bash

./build/bin/llama-server \
  --model <target.gguf> \
  --model-draft <draft.gguf> \
  --spec-type dflash:n_max=<N>,cross_ctx=<N> ...

Notes

This repo contains DFlash draft models, not a standalone instruct model.
Use it with the matching target family listed above.
Q4_K_M and Q8_0 are small test-oriented quants; create your own quant if you need a different tradeoff.

Radamanthys11/Qwen3.6-27B-DFlash-GGUF