AJ(@ItsmeAjayKV):GLM-5.3-Flash running faster on my 3090 thanks to Project Maya from @PeasantSmith ! After some tweaking (PR coming soon) i'm able to run my Aj-IQ2_XXS mixed quant with Maya. - ~20t/s avg - low 200t/s prefill. Without MTP btw. I'm working on some pr to improve speed, at this rate even GLM-5.3-flash will be usable in my 3090 before end of this month. Checkout Maya: https://t.co/TEE3KAr9te Get my quant:

@ItsmeAjayKV

Bullish on local AI OSS FTW Independent AI R&D. quants, repe, kernel. 1x 3060, 1x 3090: 64GB RAM N4 (日本語勉強中) 🎌

参加 September 2016

862 フォロー中 9.1K ファン

AJ@ItsmeAjayKV

2026.10.10 19:12

GLM-5.3-Flash running faster on my 3090 thanks to Project Maya from @PeasantSmith ! After some tweaking (PR coming soon) i'm able to run my Aj-IQ2_XXS mixed quant with Maya. - ~20t/s avg - low 200t/s prefill. Without MTP btw. I'm working on some pr to improve speed, at this rate even GLM-5.3-flash will be usable in my 3090 before end of this month. Checkout Maya: Get my quant: