Eric PRO
Ex0bit
AI & ML interests
None yet
Recent Activity
updated
a collection
about 8 hours ago
Papers updated
a collection
about 8 hours ago
Research Models updated
a collection
about 8 hours ago
Research Models Organizations
Tried requesting access, do you have to pay for access in crypto?
4
#1 opened 1 day ago
by
a2024a
For small models, Q5 and above is more robust in production?
1
#1 opened 2 days ago
by
Yhyu13
Using the Qwen3.5-9B-PRISM-DQ model will refuse to answer
1
#2 opened 2 days ago
by
xldistance
Can you create an IQ2_M quantization?
1
#1 opened 4 days ago
by
xldistance
Can you create a PRISM model of Qwen3.5-122B
3
#2 opened 7 days ago
by
xldistance
Question
8
#1 opened 13 days ago
by
rombodawg
MXFP4 for M2.5 PRISM Lite?
1
#1 opened 19 days ago
by
SabinStargem
Sponsorship request
2
#6 opened 23 days ago
by
Guilherme34
Feedback on refusal
2
#8 opened 22 days ago
by
AliceThirty
infinity loop
2
#6 opened about 2 months ago
by
FearL0rd
[Suggestion] REAP, plus IQ4_NL (for faster Apple Silicon / ARM64 inference)
1
#1 opened about 2 months ago
by
dissociativity
Intel AutoRound for best low-bit quantization
1
#5 opened about 2 months ago
by
anjeysapkovski
Req: MLX Q4 or similar for 64GB Apple Silicon?
5
#3 opened 2 months ago
by
JuanPabloski
missing tensor 'blk.92.attn_norm.weight'
9
#3 opened about 2 months ago
by
AliceThirty
Hi, could you perform the same PRISM on the Minimax M2.1?
👍 1
8
#2 opened 2 months ago
by
win10
Can we get a version that doesn't have the propaganda ?
🔥 1
9
#5 opened 2 months ago
by
trystans
error ollama run
5
#1 opened 3 months ago
by
boss003i
Request: DOI
3
#13 opened 2 months ago
by
maalikishaak
best coding&reasoning model. thank you Z.AI
👍 6
4
#10 opened 2 months ago
by
Tugay31