Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
canada-quant
/
GLM-5.3-Flash-DFlash2-F
Like
0
Follow
Canada Quant Labs
47
Text Generation
Safetensors
vllm
qwen3
speculative-decoding
dflash2
draft-model
draft
glm-5.3-flash
glm5_next
w4a16
dgx-spark
h200
b300
arxiv:
2602.06036
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
GLM-5.3-Flash-DFlash2-F
6.22 GB
Ctrl+K
Ctrl+K
1 contributor
History:
6 commits
pastapaul
Card + launcher: drafter memory cost, MTP guidance, KV default 8 GiB (2026-10-04)
f8e7677
verified
5 days ago
.gitattributes
Safe
1.52 kB
initial commit
15 days ago
PROVENANCE.txt
Safe
881 Bytes
dflash2F: DFlash2 drafter for GLM-5.3-Flash W4A16 (3.626 @K7, parity with the incoai reference on the same B300)
15 days ago
README.md
Safe
10.4 kB
Card + launcher: drafter memory cost, MTP guidance, KV default 8 GiB (2026-10-04)
5 days ago
config.json
Safe
1.97 kB
dflash2F: DFlash2 drafter for GLM-5.3-Flash W4A16 (3.626 @K7, parity with the incoai reference on the same B300)
15 days ago
launch_dflash2_tp2.sh
Safe
6.47 kB
Card + launcher: drafter memory cost, MTP guidance, KV default 8 GiB (2026-10-04)
5 days ago
mask_embedding.pt
9.88 kB
xet
dflash2F: DFlash2 drafter for GLM-5.3-Flash W4A16 (3.626 @K7, parity with the incoai reference on the same B300)
15 days ago
model.safetensors
6.22 GB
xet
dflash2F: DFlash2 drafter for GLM-5.3-Flash W4A16 (3.626 @K7, parity with the incoai reference on the same B300)
15 days ago