Tarjei Mandt
kernelpool
AI & ML interests
Everything MLX
Recent Activity
updated a model about 13 hours ago
catalystsec/gemma-4-26B-A4B-it-5bit-DWQ published a model about 13 hours ago
catalystsec/gemma-4-26B-A4B-it-5bit-DWQ liked a model about 19 hours ago
google/gemma-4-26B-A4B-itOrganizations
LongCat-Next does not emit opening tag during tool calling
1
#4 opened 2 days ago
by
kernelpool
4bit version
1
#1 opened about 2 months ago
by
ia4
Minimum RAM required to run this model
π 1
2
#1 opened 2 months ago
by
Arete7
ValueError: Model type kimi_linear not supported.
π 1
3
#1 opened 5 months ago
by
x-polyglot-x
Thankyou catalystsec for this quant
β€οΈβ 2
#2 opened 3 months ago
by
Narutoouz
Arch Error: minimax_m2
3
#3 opened 3 months ago
by
FelipeSerrano
Question about K2/V2 cache computation in prefill vs generation
2
#10 opened 3 months ago
by
kernelpool
Not working on my Macbook.
2
#1 opened 3 months ago
by
anuedaraanu
Does mlx-lm support it?
1
#1 opened 3 months ago
by
TOTORONG
ERROR:root:Model type iquestloopcoder not supported.
2
#1 opened 3 months ago
by
dmikushin
Please make 4 bit dwq mlx quant
2
#1 opened 3 months ago
by
Narutoouz
Model type llada2_moe not supported
1
#1 opened 4 months ago
by
alexchapin
4bit version
2
#1 opened 3 months ago
by
sm54
Only 4k context window?
β 2
2
#1 opened 5 months ago
by
do-me
Need assistance in running on Mac
3
#16 opened 5 months ago
by
x-polyglot-x
it doesn't work
2
#1 opened 5 months ago
by
Jack1992
runs in LMstudio
π 1
5
#1 opened 5 months ago
by
bobig
Is it possible to upload 2bit DWQ?
3
#2 opened 5 months ago
by
saviochow
MiniMax-M2-4bit not supported
2
#4 opened 5 months ago
by
garryo