Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
116.3
TFLOPS
30
3
13
Eric
PRO
Ex0bit
Follow
0xLcrgs's profile picture
NaolMengistu's profile picture
techijote's profile picture
277 followers
·
16 following
https://ko-fi.com/ex0bit
Ex0byt
eelbaz
AI & ML interests
None yet
Recent Activity
new
activity
1 day ago
Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ:
Coding Performance?
new
activity
2 days ago
Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ:
Why is using native MTP speculative decoding slower than the no-spec baseline?
new
activity
8 days ago
Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ:
Report
View all activity
Organizations
Ex0bit
's activity
All
Models
Datasets
Spaces
Buckets
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
New activity in
Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ
1 day ago
Coding Performance?
1
#6 opened 1 day ago by
Dragonite9000
New activity in
Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ
2 days ago
Why is using native MTP speculative decoding slower than the no-spec baseline?
7
#4 opened 4 days ago by
tianxiaoban
New activity in
Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ
8 days ago
Report
3
#3 opened 9 days ago by
yizhixiaoxiami
New activity in
Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ
13 days ago
I love it!
1
#2 opened 16 days ago by
pcomte
Loading Failure on LM Studio 04.13
5
#1 opened 17 days ago by
RochyRoch
New activity in
Ex0bit/Qwen3.6-27B-PRISM-EAGLE3
13 days ago
Where is the gguf?
1
#1 opened 15 days ago by
OracleToes
New activity in
Ex0bit/Gemma4-26B-A4B-PRISM-PRO-DQ-GGUF
about 2 months ago
Why "Mythos"?
🔥
7
8
#1 opened about 2 months ago by
SemKara
New activity in
Ex0bit/Kimi-K2.5-PRISM-REAP-530B-A32B
2 months ago
Has this version been uncensored ?
1
#4 opened 2 months ago by
biondogs
New activity in
Ex0bit/Qwen3.5-122B-A10B-PRISM-PRO-GGUF
3 months ago
Tried requesting access, do you have to pay for access in crypto?
4
#1 opened 3 months ago by
a2024a
New activity in
Ex0bit/Qwen3.5-PRISM-Dynamic-Quant-GGUF
3 months ago
For small models, Q5 and above is more robust in production?
1
#1 opened 3 months ago by
Yhyu13
Using the Qwen3.5-9B-PRISM-DQ model will refuse to answer
1
#2 opened 3 months ago by
xldistance
New activity in
Ex0bit/Qwen3.5-122B-A10B-PRISM-LITE-GGUF
3 months ago
Can you create an IQ2_M quantization?
1
#1 opened 3 months ago by
xldistance
New activity in
Ex0bit/Kimi-K2.5-PRISM-REAP-530B-A32B
3 months ago
Can you create a PRISM model of Qwen3.5-122B
3
#2 opened 3 months ago by
xldistance
New activity in
Ex0bit/MiniMax-M2.5-PRISM-PRO
4 months ago
Question
8
#1 opened 4 months ago by
rombodawg
New activity in
Ex0bit/MiniMax-M2.5-PRISM-LITE
4 months ago
MXFP4 for M2.5 PRISM Lite?
1
#1 opened 4 months ago by
SabinStargem
New activity in
Ex0bit/MiniMax-M2.1-PRISM
4 months ago
Sponsorship request
2
#6 opened 4 months ago by
Guilherme34
New activity in
Ex0bit/GLM-4.7-PRISM
4 months ago
Feedback on refusal
2
#8 opened 4 months ago by
AliceThirty
New activity in
Ex0bit/Step-3.5-Flash-PRISM
4 months ago
The model keeps repeating responses when running for a while, need to update to the latest llamacpp
2
#1 opened 4 months ago by
xldistance
New activity in
Ex0bit/GLM-4.7-PRISM
4 months ago
infinity loop
2
#6 opened 5 months ago by
FearL0rd
New activity in
Ex0bit/Elbaz-Prime-Intellect-3_Prism_Abliterated
5 months ago
[Suggestion] REAP, plus IQ4_NL (for faster Apple Silicon / ARM64 inference)
1
#1 opened 5 months ago by
dissociativity
Load more