Mike A

mmssix

8

AI & ML interests

None yet

Recent Activity

new activity 3 days ago

Blockway/Agens-Volundr-32B-Preview:RTX PRO 6000 Blackwell 96GB (sm120) - serving recipe + head-to-head vs Qwen3.8-27B bf16, both with DFlash2

new activity 5 days ago

piotrkosecki/Naive-N0.5-Flash-NVFP4:Working 1M context on 4x RTX PRO 6000: compact-KV plugin patch (45.8 GiB/GPU weights, needle passes to 1.03M)

new activity 18 days ago

orcarouter/GLM-5.3-Flash-Uncensored-NVFP4:This model is not operable as-is: 68.5% of expert gate/up NVFP4 global scales disagree, producing NaN logits

View all activity

Organizations

None yet

New activity in Blockway/Agens-Volundr-32B-Preview 3 days ago

RTX PRO 6000 Blackwell 96GB (sm120) - serving recipe + head-to-head vs Qwen3.8-27B bf16, both with DFlash2

#1 opened 3 days ago by

New activity in piotrkosecki/Naive-N0.5-Flash-NVFP4 5 days ago

Working 1M context on 4x RTX PRO 6000: compact-KV plugin patch (45.8 GiB/GPU weights, needle passes to 1.03M)

#1 opened 5 days ago by

New activity in orcarouter/GLM-5.3-Flash-Uncensored-NVFP4 18 days ago

This model is not operable as-is: 68.5% of expert gate/up NVFP4 global scales disagree, producing NaN logits

#4 opened 18 days ago by

New activity in caiovicentino1/DeepSeek-V4.1-Flash-HLWQ-Engram-Q4 27 days ago

SM120: patch_mask.py no longer applies to current dev-dsv41 — patch_hibrido.py is required (fix + measurements on 4x RTX PRO 6000)

#1 opened 27 days ago by

New activity in thinkingmachines/Inkling-Small-NVFP4 about 1 month ago

VRAM Usage?

#2 opened 2 months ago by

New activity in orcarouter/GLM-5.3-Flash-Uncensored-NVFP4 about 1 month ago

MTP drafter missing?

#2 opened about 1 month ago by

New activity in deepseek-ai/DeepSeek-V4-Flash-Vision-Exp about 1 month ago

vllm support

#2 opened about 1 month ago by

New activity in auroter/DeepSeek-V4-Flash-0731-NVFP4 2 months ago

Great performance on RTX 6000's

#1 opened 2 months ago by