Benchmaxxed
🧠
👍
4
2
#12 opened about 22 hours ago
by
Tom-Neverwinter
Availability of 7B and 14B models mentioned in the paper
#11 opened 1 day ago
by
Sopelllka
Question about K2/V2 cache computation in prefill vs generation
#10 opened 1 day ago
by
kernelpool
typo in readme
#9 opened 1 day ago
by
madsheepPL
need official fp8 weights
#7 opened 1 day ago
by
wangruiai2023
LM Studio Support with Q4_K_S please?
❤️
1
1
#6 opened 2 days ago
by
Cagannn
这又是谁家高手了？！
🤗
1
1
#3 opened 3 days ago
by
shangyue2333
smaller + thinking models
👍
9
#2 opened 3 days ago
by
Fizzarolli
can you share benchmarks for all models you released
#1 opened 3 days ago
by
Narutoouz