nawoa lanor
nawoalanor
AI & ML interests
None yet
Recent Activity
new activity 6 days ago
zai-org/GLM-5.3-Flash:Could've kept the active params 9b or below. new activity 6 days ago
zai-org/GLM-5.3-Flash:WE NEED 35B A3B new activity 6 days ago
zai-org/GLM-5.3-Flash:How is this "Flash"?Organizations
None yet
Could've kept the active params 9b or below.
π 1
2
#15 opened 6 days ago
by
cinnybun02
WE NEED 35B A3B
ππ₯ 18
3
#3 opened 6 days ago
by
AsThirtyThree
How is this "Flash"?
ππ₯ 25
20
#10 opened 6 days ago
by
MasterYoba
Performance results
5
#1 opened 17 days ago
by
nawoalanor
Speedup results
#1 opened 17 days ago
by
nawoalanor
Do NOT use CUDA 13.2
π€π 12
1
#2 opened 5 months ago
by
danielhanchen
Too big to run locally.
π€―π 12
21
#12 opened 4 months ago
by
Dampfinchen
427B params? This is not intelligence, its brute force.
ππ 4
17
#6 opened 3 months ago
by
Nerdsking
Abnormally poor spelling?
6
#4 opened 4 months ago
by
nawoalanor
Please release official lower-bit QAT versions
ββ€οΈ 12
2
#3 opened 3 months ago
by
nawoalanor
licence?
1
#1 opened 4 months ago
by
celikburak
This LLM is a test maxer, not a general purpose AI model.
π 3
21
#17 opened 5 months ago
by
phil111
Need a 5% and 15% REAP
7
#10 opened 5 months ago
by
nawoalanor
GLM-5.1 open οΌ >>> MiniMax-M2.7 open οΌ >>> Qwen 3.6 closed οΌ
π 2
5
#14 opened 5 months ago
by
Ai-Robots
Are some files missing??
5
#7 opened 5 months ago
by
julianchong
Minimax 2.7
#10 opened 5 months ago
by
nawoalanor
Love the license, confused by some of the decisions.
π€π 17
15
#15 opened 6 months ago
by
CyborgPaloma
All this talk about NVFP4 - why is it dog slow?
15
#13 opened 6 months ago
by
josephbreda
RTX Pro 6000 support
3
#7 opened 6 months ago
by
justinjja