Steve Li
CHNtentes
AI & ML interests
None yet
Recent Activity
new activity
about 9 hours ago
unsloth/GLM-4.7-Flash-GGUF:Jan 21: GGUFs all UPDATED!!!
new activity
1 day ago
zai-org/GLM-4.7-Flash:Problem with model
new activity
2 days ago
unsloth/GLM-4.7-Flash-GGUF:DeepSeek architecture?
Organizations
None yet
Jan 21: GGUFs all UPDATED!!!
🤗
❤️
4
39
#1 opened 2 days ago
by
danielhanchen
Problem with model
5
#22 opened 2 days ago
by
dwojcik
DeepSeek architecture?
5
#2 opened 2 days ago
by
spanspek
mtp support?
1
#4 opened 2 days ago
by
CHNtentes
zimage far better than this glm-image
👀
👍
4
10
#1 opened 8 days ago
by
llamameta
KV Cache per token and Doubling the context size
3
#12 opened 10 days ago
by
HenkTenk
Repeats a single word or phrase endlessly every single time I try to prompt
10
#1 opened 9 days ago
by
Disdrix
Using "IQuest-Coder-V1-40B-Loop-Instruct" on Cursor
2
#14 opened 18 days ago
by
Maub69
What vLLM version should I use to deploy this model?
3
#13 opened 18 days ago
by
yyg201708
Report: getting 20 t/s with UD-Q4_K_XL and 72 VRAM
🔥
1
10
#2 opened 27 days ago
by
SlavikF
Q4_K_M is bigger than Q4_K_XL
2
#7 opened 24 days ago
by
ru5h
Question about group size
2
#1 opened about 1 month ago
by
nephepritou
Jinja模板是不是有问题
3
#14 opened 29 days ago
by
pty819
May I ask when the minimax m2.1 will be released
➕
5
4
#48 opened about 1 month ago
by
zhangjian95
Request for UD versions of larger quants like Q6_K
2
#1 opened about 1 month ago
by
mingyi456
压缩是为了降低计算量并增强大模型的性能, 那为啥不使用北大提出的iFairy 2位复数量化方案?
❤️
👍
1
#1 opened 3 months ago
by
everboat
Jan 12 2026: Qwen3-Next updated with iMatrix + Improved performance!
👍
3
25
#3 opened about 2 months ago
by
danielhanchen
After a long time, finally a capable little coder!
😎
❤️
3
7
#2 opened about 2 months ago
by
MrDevolver
It's really top_k = 2?
👍
2
1
#6 opened about 1 month ago
by
CHNtentes