PhalaCloud/GLM-5.3-W4AFP8
Text Generation • 386B • Updated • 4.21k • 10
Hang Yin
h4x3rotab
AI & ML interests
Private and verifiable AI.
Recent Activity
new activity 16 days ago
PhalaCloud/GLM-5.3-W4AFP8:Is it possible to build a GLM-5.3-Flash-W4AFP8? new activity 17 days ago
PhalaCloud/GLM-5.3-W4AFP8:The performance of glm updated a model 27 days ago
PhalaCloud/GLM-5.3-W4AFP8Organizations
Is it possible to build a GLM-5.3-Flash-W4AFP8?
1
#1 opened 25 days ago
by 
iwoolk
The performance of glm
1
#2 opened 17 days ago
by 
jianjungki
updated a
model 27 days ago
liked a
model 27 days ago
W4AFP8 for 5.3
6
#7 opened about 1 month ago
by 
jlondon
published a
model 29 days ago
updated a
model 2 months ago
published a
model 2 months ago
updated a
model 2 months ago
ERROR: Should have a `model_type` key in its config.json
1
#5 opened 3 months ago
by 
PakJoeng
8xH20 141GB cuda out of memory
1
#6 opened 3 months ago
by 
ErisLU
Any chances for A100?
1
#4 opened 3 months ago
by 
traphix
GLM-5.2-W4AFP8 on 8×H100: fp8_e4m3 KV cache produces corrupted output, while BF16 KV works correctly
1
#3 opened 3 months ago
by 
loveblairsky
Is the quantize script opensource?
3
#2 opened 3 months ago
by 
wxsm
KTransformers + SGLang
1
#1 opened 3 months ago
by 
mtcl
liked a
model 3 months ago
published a
model 3 months ago
liked a
dataset 5 months ago