exllamav3 quantizations of TheDrummer's Artemis-31B-v1.2.
Quantized using 12414d0 of the dev branch. Requires exllamav3-v1.5.1 or above.
2.25bpw_h6 11.761 GiB
4.00bpw_h6 17.730 GiB
6.00bpw_h8 24.877 GiB (this model)
Original model card follows below.
Model Card WIP
Usage
- Gemma 4 31B template, thinking or non-thinking.
- Sampler wrangling may be required (or be conservative)
- Gemma thinking is razor sharp for RP
- Crowdsourced Samplers
- Share your samplers!
config-v1q
- Downloads last month
- 21
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support