Hugging Face
Search models, datasets, users...
Ctrl K
Models
Datasets
Spaces
Buckets
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
37.1
TFLOPS
Jürgen Schmied
josch15366
14
Follow
velaia's profile picture
webbrain-one-240398's profile picture
2 followers
·
1 following
AI & ML interests
None yet
Recent Activity
updated
a model
about 1 month ago
josch15366/Kolibri-1-block-drafter
published
a model
about 1 month ago
josch15366/Kolibri-1-block-drafter
published
a model
about 1 month ago
josch15366/Kolibri-1-EAGLE3-drafter
View all activity
Organizations
None yet
josch15366
's activity
All
Models
Datasets
Spaces
Buckets
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
updated
a model
about 1 month ago
josch15366/Kolibri-1-block-drafter
0.4B
•
Updated
Oct 10
•
36
published
2 models
about 1 month ago
josch15366/Kolibri-1-block-drafter
0.4B
•
Updated
Oct 10
•
36
josch15366/Kolibri-1-EAGLE3-drafter
90.4M
•
Updated
Oct 6
•
43
•
3
updated
a model
about 1 month ago
josch15366/Kolibri-1-EAGLE3-drafter
90.4M
•
Updated
Oct 6
•
43
•
3
New activity in
RadixArk/Qwen3.8-Flash-Next-NVFP4
2 months ago
Recipe for vllm
🔥
1
1
#9 opened 2 months ago by
josch15366
New activity in
josch15366/Qwen3.8-Flash-Next-NVFP4-LocalHessian-Experts
2 months ago
Calibration corpus: what we got wrong, and the one thing worth copying (position stratification)
#1 opened 2 months ago by
josch15366
New activity in
RadixArk/Qwen3.8-Flash-Next-NVFP4
2 months ago
Per-expert weight_scale_2 is worth ~0.9 % held-out NLL (and two contracts you got right)
#13 opened 2 months ago by
josch15366
updated
a model
2 months ago
josch15366/Qwen3.8-Flash-Next-NVFP4-LocalHessian-Experts
Updated
Sep 11
published
2 models
2 months ago
josch15366/Qwen3.8-Flash-Next-NVFP4-LocalHessian-Experts
Updated
Sep 11
josch15366/Qwen3.8-Flash-Next-FP8-lm_head
Updated
Sep 10
updated
2 models
2 months ago
josch15366/Qwen3.8-Flash-Next-FP8-lm_head
Updated
Sep 10
josch15366/Qwen3.8-27B-DFlash2-FP8
2B
•
Updated
Sep 10
•
147
•
2
New activity in
tcclaviger/Qwen3.8-27B-DFlash2-FP8
3 months ago
rationale for this build
3
#1 opened 3 months ago by
josch15366
New activity in
syvai/Qwen3.8-27B-DFlash2-W4A16
3 months ago
Best speed in fleet
1
#1 opened 3 months ago by
josch15366
New activity in
RadixArk/Qwen3.8-27B-NVFP4
3 months ago
The DFlash2 restriction behind the BF16 lm_head change was removed upstream a day earlier
2
#3 opened 3 months ago by
josch15366
New activity in
unsloth/Qwen3.8-27B-NVFP4
3 months ago
Any chance of Unsloth's Qwen3.8 27B NVFP4 DSPARK/DFLASH2?
13
#20 opened 3 months ago by
MaMo7x
published
a model
3 months ago
josch15366/Qwen3.8-27B-DFlash2-FP8
2B
•
Updated
Sep 10
•
147
•
2
New activity in
RadixArk/Qwen3.8-27B-DSpark
3 months ago
Drafter is for fp8 and does not work on nvfp4
➕
5
3
#4 opened 3 months ago by
josch15366
New activity in
Inferact/Qwen3.8-27B-NVFP4
3 months ago
unsloth/Qwen3.8-27B-NVFP4 vs. Inferact/Qwen3.8-27B-NVFP4?
🔥
➕
3
10
#1 opened 3 months ago by
pathosethoslogos
New activity in
RadixArk/Qwen3.8-27B-DSpark
3 months ago
[BUG] DSpark slower than EAGLE + severe cold-start penalty
7
#3 opened 3 months ago by
voves
Load more