canada-quant/hy3-w4a16-mtp
Text Generation • 47B • Updated • 1.9k • 5
AI & ML interests
Canada Quant Labs — Canada's open-weight model lab. We train, quantize, and ship sovereign reference models for regulated industries (legal, medical, defence, finance) on a DGX B300 at Equinix Vancouver. Upstream contributors to vLLM and llm-compressor. Recipes: W4A16, NVFP4, MXFP4. Built in Victoria, BC. partnerships@cql.ca · cql.ca
Recent Activity
View all activity
pastapaul
updated a
model 21 days ago
pastapaul
updated a
dataset 21 days ago
pastapaul
published a
dataset 21 days ago
pastapaul
updated a
Space 23 days ago
pastapaul
published a
model 25 days ago
Loading the model
4
#1 opened about 1 month ago
by 
madeby561
pastapaul
updated a
model about 1 month ago
Can you run NVFP4 + Marlin?
5
#2 opened about 1 month ago
by 
einsteiner1983
pastapaul
published a
model about 1 month ago
Docker Image
8
#1 opened 2 months ago
by 
mtcl
Compatible version with Ampere? SM8.6
1
#6 opened 2 months ago
by 
bullerwins
Small patch to fix MTP on current vLLM (8th of June, 26)
7
#8 opened 2 months ago
by 
dnhkng
MTP BF16 draft weights may need explicit quant_config exclusion for vLLM
2
#2 opened 2 months ago
by 
yangsiqt2
pastapaul
updated a
model 2 months ago
pastapaul
updated a
dataset 2 months ago
pastapaul
published a
dataset 2 months ago
pastapaul
updated a
model 2 months ago
2026-05-26 dual-spark bench: GSM8K 94-98%, AIME 4/5, concurrency wall 12→125 tok/s
#7 opened 2 months ago
by 
pastapaul
Lossless?
👀 1
1
#1 opened 2 months ago
by 
lukealonso