Finding 1
finding1
AI & ML interests
None yet
Organizations
None yet
What sampler settings were used to achieve the reported benchmark scores?
👀
1
2
#8 opened 3 months ago
by
finding1
Is this upload motivated by known problems in older 8-bit MLX quants of Qwen3-0.6B?
#1 opened 3 months ago
by
finding1
Q8 version please
2
#2 opened 5 months ago
by
acediac
Llama 4 GGUFs now with multimodal (image) capabilities.
9
#5 opened 7 months ago
by
shimmyshimmer
Q4_K_M missing blk.8.ffn_up_exps.weight
1
#1 opened 7 months ago
by
finding1
Q4_K_M missing blk.8.ffn_up_exps.weight
1
#1 opened 7 months ago
by
finding1