Zhi Jin
zhijin123
AI & ML interests
None yet
Recent Activity
liked a model 3 days ago
mradermacher/Arete-27B-Unlocked-Uncensored-Heretic-GGUF liked a model 3 days ago
mradermacher/Arete-27B-Unlocked-Uncensored-Heretic-i1-GGUF liked a model 4 days ago
bartowski/NousResearch_Arete-27B-GGUFOrganizations
None yet
Able to run the L version with 2gigs free and full context/history. Thank you!
❤️🚀 1
3
#10 opened 21 days ago
by
SeattleSysop
Good to have Q2_0 for llama.cpp. It is great.
#111 opened 9 days ago
by
zhijin123
Will Kolibri-1 support vision later?
#19 opened 21 days ago
by
zhijin123
Will this model support vision?
#7 opened about 1 month ago
by
zhijin123
IQ3_S is pretty much BF16
👍🚀 5
9
#32 opened about 2 months ago
by
dandandelion
When use llama.cpp, do i need to set --reasoning-format deepseek?
#7 opened about 1 month ago
by
zhijin123
Solved "xhigh" loop and include MTP. Test on 4080 12G VRAM laptop, reach ~60 t/s
👍🚀 3
#45 opened about 2 months ago
by
zhijin123
Share my fix (on/off thought content) when running nex-m2-mini gguf with llama.cpp
2
#2 opened 5 months ago
by
zhijin123
Share my fix (on/off thought content) when running nex-m2-mini gguf with llama.cpp.
#3 opened 5 months ago
by
zhijin123
Can i use Qwopus3.6-27B-Coder-MTP-GGUF to replace Qwopus3.6-27B-v2-MTP?
3
#2 opened 5 months ago
by
zhijin123
Will have "Balanced" version later?
1
#30 opened 5 months ago
by
zhijin123
Qwen3.6-35B-A3B-MTP-GGUF moe model has no obviously benefit from MTP
5
#5 opened 6 months ago
by
zhijin123
Qwen3.6-35B-A3B-MTP-GGUF moe model has no obviously benefit from MTP
5
#5 opened 6 months ago
by
zhijin123