plz
qenme
ยท
AI & ML interests
None yet
Recent Activity
new activity about 7 hours ago
ubergarm/Kimi-K2.6-GGUF:Q4_X on Blackwell + EPYC + DDR 5 new activity 8 days ago
cyankiwi/Qwen3.6-27B-AWQ-BF16-INT8:Compatible with vLLM on Ampere? new activity 20 days ago
RedHatAI/gemma-4-31B-it-FP8-dynamic:Can you add more details to the model card?Organizations
None yet
Q4_X on Blackwell + EPYC + DDR 5
๐๐ฅ 4
13
#3 opened 3 months ago
by
sousekd
Compatible with vLLM on Ampere?
โ 4
7
#3 opened about 2 months ago
by
HenkTenk
Can you add more details to the model card?
6
#1 opened 3 months ago
by
bullerwins
26b with w416a-ct
1
#3 opened 28 days ago
by
meganoob1337
Gemma team in the back making shrimp fried rice!!!!
๐ฅ 1
#1 opened 30 days ago
by
qenme
KL divergence benchmark
2
#3 opened about 1 month ago
by
qenme
Tokenizer problems, or just quants?
2
#105 opened about 2 months ago
by
nesymerp1
Me again
3
#2 opened about 2 months ago
by
qenme
MTP support?
๐ 1
8
#5 opened about 2 months ago
by
Nindaleth
Very bad results with model quant and KV cache quant, only BF16 works well
๐๐ 5
4
#34 opened 2 months ago
by
qenme
F16 or BF16?
5
#6 opened about 2 months ago
by
qenme
FYI : --spec-type mtp syntax has changed to --spec-type draft-mtp
๐ 3
3
#14 opened about 2 months ago
by
qenme
presence-penalty
5
#8 opened about 2 months ago
by
owao
Good quant!
12
#1 opened 2 months ago
by
qenme
Working good on 96GB VRAM + DDR5 Setup
โค๏ธ 1
5
#2 opened 2 months ago
by
phakio
GOOLE WHERE IS MTP ?
๐ฅ 2
2
#82 opened 2 months ago
by
EvilinaMaller
10/10
๐ฅ 6
1
#4 opened 2 months ago
by
qenme
thanks!
โโค๏ธ 19
2
#1 opened 2 months ago
by
qenme
Will there be a small model for speculative decoding?
3
#71 opened 3 months ago
by
Regrin