maglat
maglat
·
AI & ML interests
None yet
Recent Activity
new activity 2 days ago
avtc/Hy3-GPTQ-RTN-4bit-tp8:Works with 8 RTX3090 liked a model 2 days ago
avtc/Hy3-GPTQ-RTN-4bit-tp8 new activity 2 days ago
unsloth/DeepSeek-V4-Flash-GGUF:DeepSeek-V4-Flash is now ready to run locally! 🐳Organizations
None yet
Works with 8 RTX3090
🤗 1
5
#2 opened 2 days ago
by
maglat
DeepSeek-V4-Flash is now ready to run locally! 🐳
❤️👍 7
17
#6 opened 4 days ago
by
danielhanchen
Finally! 🎉
🤗🔥 7
3
#1 opened 5 days ago
by
agikeen
Please wait for official announcement before using!
🧠🚀 9
6
#5 opened 4 days ago
by
danielhanchen
More Quants Coming?
5
#1 opened 7 days ago
by
maglat
122b and vision possible?
👀➕ 15
#3 opened 15 days ago
by
maglat
how to use it
10
#1 opened about 1 month ago
by
iSource1
mmproj file?
5
#1 opened 2 months ago
by
Grossor
Smaller variants
👍 1
6
#8 opened 27 days ago
by
nonetrix
Gemma 4:124b
👍🚀 90
18
#1 opened about 1 month ago
by
seamon67
MTP-layer weights?
👀➕ 9
11
#1 opened about 1 month ago
by
CosmicRaisins
Request Step 3.7 Flash
#9 opened about 1 month ago
by
maglat
Spiritbuun Qwen3.6 Chat Template relevant?
👀 2
#3 opened about 2 months ago
by
maglat
hello,The model's output is garbled.
8
#1 opened about 2 months ago
by
zhao198300
v2 variant?
➕ 3
3
#8 opened about 2 months ago
by
maglat
FP8 variant possible?
2
#1 opened about 2 months ago
by
maglat
AWQ of Qwopus3.6-27B-v2
#4 opened about 2 months ago
by
maglat
Is it compatible with qwen?
3
#3 opened 4 months ago
by
k3soft
My deepest respect and admiration goes out to the Qwen team!!
👍❤️ 65
16
#1 opened 3 months ago
by
testamentaddress01
Many thanks!
👍 9
4
#4 opened 3 months ago
by
maglat