RedHatAI / gemma-4-31B-it-speculator.dflash

huggingface.co
Total runs: 4.7K
24-hour runs: 0
7-day runs: 2
30-day runs: 1.8K
Model's Last Updated: May 26 2026

Introduction of gemma-4-31B-it-speculator.dflash

Model Details of gemma-4-31B-it-speculator.dflash

RedHatAI/gemma-4-31B-it-speculator.dflash

This is a preliminary (and subject to change) DFlash speculator model for google/gemma-4-31B-it .

It was trained using the Speculators library on a combination of the Magpie-Align/Magpie-Llama-3.1-Pro-300K-Filtered dataset and the train_sft split of the HuggingFaceH4/ultrachat_200k dataset. Training data used Magpie + UltraChat with responses from the gemma-4-31B-it model (no reasoning) .

This model should be used with the google/gemma-4-31b-it chat template, specifically through the /chat/completions endpoint.

Note:

It was validated on Nvidia H100, other hardware validation pending.

We are continuing to train this model and will update with more evaluations and new weights in the future.

Deployment

Deploy with vLLM (main) using the speculator as a draft model:

vllm serve -tp 2 RedHatAI/gemma-4-31B-it-speculator.dflash --attention-backend FLASH_ATTN
Preliminary Evaluations

Evaluation command:

vllm bench serve --backend openai-chat --endpoint /v1/chat/completions \
  --dataset-name hf --tokenizer google/gemma-4-31B-it \
  --dataset-path "philschmid/mt-bench" --num-prompts 80 \
  --max-concurrency 1 --model RedHatAI/gemma-4-31B-it-speculator.dflash \
  --hf-output-len 2048 \
  --temperature 0 --save-result --save-detailed

MT-Bench Per-Position Acceptance Rate

Position Acceptance (%)
0 71.94
1 46.14
2 29.08
3 19.42
4 13.74
5 9.18
6 6.19
7 3.79

Runs of RedHatAI gemma-4-31B-it-speculator.dflash on huggingface.co

4.7K
Total runs
0
24-hour runs
48
3-day runs
2
7-day runs
1.8K
30-day runs

More Information About gemma-4-31B-it-speculator.dflash huggingface.co Model

More gemma-4-31B-it-speculator.dflash license Visit here:

https://choosealicense.com/licenses/apache-2.0

gemma-4-31B-it-speculator.dflash huggingface.co

gemma-4-31B-it-speculator.dflash huggingface.co is an AI model on huggingface.co that provides gemma-4-31B-it-speculator.dflash's model effect (), which can be used instantly with this RedHatAI gemma-4-31B-it-speculator.dflash model. huggingface.co supports a free trial of the gemma-4-31B-it-speculator.dflash model, and also provides paid use of the gemma-4-31B-it-speculator.dflash. Support call gemma-4-31B-it-speculator.dflash model through api, including Node.js, Python, http.

gemma-4-31B-it-speculator.dflash huggingface.co Url

https://huggingface.co/RedHatAI/gemma-4-31B-it-speculator.dflash

RedHatAI gemma-4-31B-it-speculator.dflash online free

gemma-4-31B-it-speculator.dflash huggingface.co is an online trial and call api platform, which integrates gemma-4-31B-it-speculator.dflash's modeling effects, including api services, and provides a free online trial of gemma-4-31B-it-speculator.dflash, you can try gemma-4-31B-it-speculator.dflash online for free by clicking the link below.

RedHatAI gemma-4-31B-it-speculator.dflash online free url in huggingface.co:

https://huggingface.co/RedHatAI/gemma-4-31B-it-speculator.dflash

gemma-4-31B-it-speculator.dflash install

gemma-4-31B-it-speculator.dflash is an open source model from GitHub that offers a free installation service, and any user can find gemma-4-31B-it-speculator.dflash on GitHub to install. At the same time, huggingface.co provides the effect of gemma-4-31B-it-speculator.dflash install, users can directly use gemma-4-31B-it-speculator.dflash installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

gemma-4-31B-it-speculator.dflash install url in huggingface.co:

https://huggingface.co/RedHatAI/gemma-4-31B-it-speculator.dflash

Url of gemma-4-31B-it-speculator.dflash

gemma-4-31B-it-speculator.dflash huggingface.co Url

Provider of gemma-4-31B-it-speculator.dflash huggingface.co

RedHatAI
ORGANIZATIONS

Other API from RedHatAI

huggingface.co

Total runs: 26.2K
Run Growth: -15.7K
Growth Rate: -59.90%
Updated:May 18 2026
huggingface.co

Total runs: 20.9K
Run Growth: -11.8K
Growth Rate: -56.48%
Updated:April 29 2026