p w
SassyDiffusion
AI & ML interests
None yet
Organizations
None yet
Wrong metadata file_type or file name?
3
#2 opened 2 months ago
by
mepstein
Bro....500多B的Flash,8卡H200已经上不了桌了吗[cry]
9
#16 opened 2 months ago
by
Saito-Karuha
UD-Q4_K_XL expected strong performance drop compared to AtomicChats's Q4_K_M?
4
#1 opened 2 months ago
by
NamerPRO
Is the n-gram chunk embedded in the gguf(s), and is it ~51GB independent of quantization?
14
#35 opened 3 months ago
by
dagb
Is it possible to offload n-gram to an NVMe SSD?
👀🚀 31
15
#11 opened 3 months ago
by
lingyezhixing
How much VRAM do you need to run this model?
👀 1
11
#7 opened 3 months ago
by
ntp777
Deceptive Model Card
👍 5
2
#6 opened 5 months ago
by
sheliak
New version?
5
#1 opened 6 months ago
by
AI-Joe-git
jinja template update
6
#3 opened 6 months ago
by
SassyDiffusion
amazing !
👍🚀 2
14
#1 opened 7 months ago
by
Strongzero0
Can we get Qwen3.6-35B-A3B ARA GGUFs?
7
#1 opened 7 months ago
by
zzxc3c
Gemma 4 26B-A4B GGUF Benchmarks
👍🔥 12
6
#35 opened 7 months ago
by
danielhanchen
~47000 prompt tokens
2
#3 opened 7 months ago
by
zzxc3c
New chat template fixes
3
#2 opened 7 months ago
by
zzxc3c
Q6_K_L please
2
#1 opened 7 months ago
by
Vlad100
Are you planning a heretic version of Qwen3.5‑122B?
👍 1
6
#1 opened 8 months ago
by
Swat007
Better Sample Images
🤯❤️ 18
16
#6 opened 10 months ago
by
velezbeltran
Qwen-Image-Layered?
1
#5 opened 11 months ago
by
SassyDiffusion
text bench compare with GLM 4.6 normal.
👍 2
1
#3 opened 11 months ago
by
yuchenxie
Great Quant !
🔥 1
12
#1 opened about 1 year ago
by
bobig