floory
floory
AI & ML interests
None yet
Recent Activity
new activity about 11 hours ago
magiccodingman/Qwen3.6-35B-A3B-MagicQuant-GGUF:qwen3.6 27b liked a model 6 days ago
spiritbuun/Qwen3.6-27B-DFlash-GGUF liked a model 13 days ago
OpenMOSS-Team/MOSS-TTS-Nano-100MOrganizations
None yet
qwen3.6 27b
๐ฅ 1
1
#1 opened about 11 hours ago
by
floory
Qwen3.6 GGUF Benchmarks
๐ฅ๐ 21
25
#10 opened 14 days ago
by
danielhanchen
The model refuses to do research
1
#3 opened 21 days ago
by
dicksondickson
transparency regarding quants
๐ค 1
1
#6 opened 15 days ago
by
floory
MagicQuant for Apriel 1.6?
7
#1 opened 3 months ago
by
sebastienbo
nice model lol
#1 opened about 1 month ago
by
floory
so the quant is worse than Q4_K_M?
#1 opened about 2 months ago
by
floory
Massive clipping damage? Why is Q8KXL have F16 tensors/layers when it's a native BF16 model?
๐ 1
8
#3 opened about 2 months ago
by
RyanoSaurus-Wrex
issue with quant
1
#1 opened 2 months ago
by
floory
TQ1 quant?
๐ 2
3
#6 opened 2 months ago
by
sergeysi
Is there some helpful regex to offload all MoE layers to the CPU?
4
#7 opened 2 months ago
by
hdnh2006
Q3_K_XL?
๐ 2
6
#2 opened 2 months ago
by
floory
wrong title
2
#1 opened 3 months ago
by
floory
Dataset?
1
#1 opened 3 months ago
by
floory
iMatrix
๐ 7
#1 opened 3 months ago
by
floory
Failed to initialize the context: quantized V cache was requested, but this requires Flash Attention
2
#4 opened 3 months ago
by
SilverJim
A low number of evaluation benchmarks
2
#5 opened 3 months ago
by
Michalea
๐ฉ Report: Spam
#1 opened 3 months ago
by
floory