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-E
Like
2
Follow
Canada Quant Labs
48
Text Generation
Safetensors
vllm
qwen3
speculative-decoding
dflash2
draft-model
draft
glm-5.3-flash
glm5_next
w4a16
dgx-spark
h200
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-E
6.22 GB
Ctrl+K
Ctrl+K
1 contributor
History:
11 commits
pastapaul
Card + launcher: drafter memory cost, MTP guidance, KV default 8 GiB (2026-10-04)
7aa3841
verified
15 days ago
.gitattributes
Safe
1.52 kB
initial commit
about 1 month ago
PROVENANCE.txt
Safe
883 Bytes
Release dflash2E: DFlash2 drafter for GLM-5.3-Flash (weights sha af0d8d16, config 699bdf29, mask 2474994c) + model card
about 1 month ago
README.md
Safe
11.4 kB
Card + launcher: drafter memory cost, MTP guidance, KV default 8 GiB (2026-10-04)
15 days ago
config.json
Safe
1.97 kB
Release dflash2E: DFlash2 drafter for GLM-5.3-Flash (weights sha af0d8d16, config 699bdf29, mask 2474994c) + model card
about 1 month ago
launch_dflash2_tp2.sh
Safe
6.47 kB
Card + launcher: drafter memory cost, MTP guidance, KV default 8 GiB (2026-10-04)
15 days ago
mask_embedding.pt
Safe
9.88 kB
xet
Release dflash2E: DFlash2 drafter for GLM-5.3-Flash (weights sha af0d8d16, config 699bdf29, mask 2474994c) + model card
about 1 month ago
model.safetensors
Safe
6.22 GB
xet
Release dflash2E: DFlash2 drafter for GLM-5.3-Flash (weights sha af0d8d16, config 699bdf29, mask 2474994c) + model card
about 1 month ago
