Smc
sm54
AI & ML interests
None yet
Recent Activity
new activity 21 days ago
mlx-community/Qwen3.5-397B-A17B-nvfp4:Issue with quant new activity about 1 month ago
Qwen/Qwen3.5-397B-A17B:Template issue maybe new activity about 1 month ago
mlx-community/Qwen3.5-397B-A17B-4bit:NVFP4 MLXOrganizations
None yet
Issue with quant
#3 opened 21 days ago
by
sm54
Template issue maybe
👍 1
1
#23 opened about 1 month ago
by
sm54
NVFP4 MLX
3
#3 opened about 1 month ago
by
sm54
4bit version
2
#1 opened 3 months ago
by
sm54
Replicate perplexity test
1
#3 opened 5 months ago
by
sm54
Actually slower than Q4K and Q3K quants
3
#1 opened 5 months ago
by
Lockout
New REAP GLM 4.6!!!
2
#2 opened 5 months ago
by
InfernalDread
GGUF quant
➕ 3
2
#3 opened 5 months ago
by
sm54
Dwq quant
1
#1 opened 5 months ago
by
sm54
Dwq version
#2 opened 6 months ago
by
sm54
Make sure to use the latest version of llama CPP to run this model
👍 1
#1 opened 6 months ago
by
sm54
Hello, its me again, Back at it with another GLM Model!
❤️ 1
5
#1 opened 6 months ago
by
InfernalDread
Is it possible to do this for the full GLM 4.5?
7
#1 opened 7 months ago
by
InfernalDread
How to turn on thinking in LM Studio with ds 3.1?
1
#7 opened 7 months ago
by
10mmlover
Recent changes
1
#8 opened 7 months ago
by
sm54
Model broken
👍 4
11
#4 opened 10 months ago
by
sm54
Bartowski! 0.0!!!! You are on double-secret probation for this jinja error!
7
#4 opened about 1 year ago
by
rkh661
Lighter and Faster
1
#1 opened about 1 year ago
by
bobig
Thank you
4
#1 opened about 1 year ago
by
bobig