Zhang Shibu
shibuzhang
AI & ML interests
None yet
Recent Activity
new activity about 21 hours ago
AliceThirty/GLM-5.3-Flash-UNCENSORED-GGUF:Q5_K_XL liked a model 4 days ago
zai-org/GLM-5.3 liked a model 5 days ago
Blackfrost-AI/GLM-5.3-Flash-DERISKED-BF16Organizations
None yet
建议出Q4_K_M及以上量化的
👍 1
7
#3 opened about 1 month ago
by
sndnnlfhvk
model speed feedback
2
#1 opened 6 months ago
by
shibuzhang
smaller model
👍 2
2
#18 opened 11 months ago
by
spinochenza
Has anyone successfully loaded q8_0 gguf?
3
#7 opened 11 months ago
by
rthug
very good for role-playing
👍 1
1
#5 opened 11 months ago
by
Kartoshka20012
Thank you! Just a thought - would it be worth exploring the quantized version of mxfp4 technology?
#2 opened 11 months ago
by
shibuzhang
Great Model, but Quantization Issues Impact Performance
➕ 1
1
#1 opened about 1 year ago
by
shibuzhang
Any plans on 30B-A3B model?
🔥 31
7
#1 opened over 1 year ago
by
xxx777xxxASD
Feedback
1
#2 opened over 1 year ago
by
ChuckMcSneed
not as good as the previously released abliterated model
3
#3 opened over 1 year ago
by
EnumaElish123
the abliteration doesn't work
4
#2 opened over 1 year ago
by
CrestYao
第一印象:有点傻
3
#13 opened almost 2 years ago
by
TouchNight
Best model i've tried (sometimes?)
7
#1 opened over 2 years ago
by
saishf
70B-Chinese in the future?
5
#27 opened over 2 years ago
by
woshimark666