EXL3 quants of DeepSeek-V4.1-Flash-1017

⚠️ Requires ExLlamaV3 v1.6.6 (or dev branch)

SC quants:

1.68 bits per weight
2.25 bits per weight
2.68 bits per weight

qb_kld qb_ppl_vram

quant AIME-25 GPQA-D
1.68 bpw 96.7% 90.4%
2.25 bpw 100% 90.4%
2.68 bpw 100% 89.9%
baseline 100%¹ 90.2%²

¹ Assumed, given quant scores, couldn't find a source
² From OpenRouter

(more quants to follow, along with more benchmarks)

If you get corrupted output on short prompts, it is likely just a failure mode of the model itself. See here.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for turboderp/DeepSeek-V4.1-Flash-1017-exl3

Quantized
(174)
this model

Collection including turboderp/DeepSeek-V4.1-Flash-1017-exl3