You can deploy this model and start earning money today!

Radamanthys11/
Gemma-4-31B-it-DFlash-GGUF

Name: Gemma-4-31B-it-DFlash-GGUF
Availability: InStock

z-lab/gemma-4-31B-it-DFlash

quantized

endpoints_compatible

feature-extraction

Views

No views yet

Gemma 4 31B 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/gemma-4-31B-it-DFlash.

Compatible target model

google_gemma-4-31B-it.gguf - Mainly tested with Q8_0.

Files

File	Quant	Size
`gemma4-31b-it-dflash-F16.gguf`	F16	2.9 GB
`gemma4-31b-it-dflash-Q8_0.gguf`	Q8_0	1.6 GB
`gemma4-31b-it-dflash-Q4_K_M.gguf`	Q4_K_M	871 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/Gemma-4-31B-it-DFlash-GGUF