FrenzyBiscuit
FrenzyBiscuit
AI & ML interests
None yet
Recent Activity
new activity
about 5 hours ago
ReadyArt/Cydonia-24B-v2.1_EXL2_5.0bpw_H8:Lovely model, hope there is a 5.5bpw version
new activity
about 13 hours ago
ReadyArt/QwQ-32B-Snowdrop-v0_EXL2_4.0bpw_H8:[Suggestion] Proper quantization labelling, attribution
updated
a model
about 13 hours ago
ReadyArt/QwQ-32B-Snowdrop-v0_EXL2_8.0bpw_H8
Organizations
FrenzyBiscuit's activity
Lovely model, hope there is a 5.5bpw version
3
#1 opened 1 day ago
by
cactopus
[Suggestion] Proper quantization labelling, attribution
9
#1 opened 4 days ago
by
finis-est

Qwen 2.5 32B 1M version?
1
#6 opened about 2 months ago
by
FrenzyBiscuit

EXL2 Request Thread
#1 opened about 2 months ago
by
FrenzyBiscuit

This is a great model
2
#1 opened about 2 months ago
by
FrenzyBiscuit

Speculative Decoding
#1 opened about 2 months ago
by
FrenzyBiscuit

4.5 or 4.65bpw
4
#1 opened 3 months ago
by
Gesard
What's the correct chat template?
2
#3 opened 3 months ago
by
FrenzyBiscuit

Weights
#1 opened 3 months ago
by
FrenzyBiscuit

EXL2 quants available
#2 opened 3 months ago
by
FrenzyBiscuit

Updated v0.2 model?
1
#1 opened 3 months ago
by
FrenzyBiscuit

Repetitive issues
#2 opened 3 months ago
by
FrenzyBiscuit
