Product-VQ codebook weights (NVFP4-CB / FP8-CB) served by stock vLLM on Blackwell tensor cores. Spec + plugin: github.com/RobTand/gridbook
Rob
rdtand
AI & ML interests
None yet
Recent Activity
liked a model 24 days ago
deepseek-ai/DeepSeek-V4.1-Flash-1017 updated a model about 2 months ago
rdtand/q7m9-r2 published a model about 2 months ago
rdtand/q7m9-r2Organizations
None yet
models 25
rdtand/q7m9-r2
168B • Updated • 8
rdtand/Qwen3.8-27B-PrismaScout-AQUA-Vision-20GB
Image-Text-to-Text • 17B • Updated • 414 • 5
rdtand/Qwen3.6-27B-PrismaSCOUT-Blackwell-NVFP4-BF16-vllm
15B • Updated • 438 • 44
rdtand/Qwen3.8-27B-PrismaScout-AQUA-20GB
Text Generation • 17B • Updated • 73 • 3
rdtand/Qwen3.8-27B-PrismaAQUA-5.5bit-vllm
Image-Text-to-Text • 19B • Updated • 619 • 29
rdtand/DeepSeek-V4-Flash-0731-PrismaQuant-AQUA-gridbook-87GB-spark-vllm
85B • Updated • 72 • 4
rdtand/Ornith-1.5-35B-A3B-PrismaQuant-AQUA-25GB-vllm
Text Generation • 20B • Updated • 152 • 1
rdtand/Qwen3.8-27B-PrismaAQUA-gridbook-13GB-5080-vllm
Text Generation • 12B • Updated • 123 • 4
rdtand/Hy3-295B-A21B-prismaquant-gridbook-2.9bit-vllm
Text Generation • 104B • Updated • 11 • 3
rdtand/Laguna-S-2.1-prismaquant-gridbook-6bit-vllm
Text Generation • 85B • Updated • 15 • 8
datasets 0
None public yet