unsloth/LFM2.5-230M
Text Generation • 0.2B • Updated • 972 • 7
AI & ML interests
Open Source AI 🦥
Recent Activity
View all activity
1-bit GLM-5.2 GGUF vs. Claude 4.8 Opus vs. GPT-5.5
🔥👍 11
6
#10 opened 5 days ago
by 
danielhanchen
danielhanchen
updated 2
models 3 days ago
danielhanchen
published 2
models 3 days ago
mmproj file so small!
7
#1 opened 4 days ago
by 
CHHORVORN
mmproj file so small!
7
#1 opened 4 days ago
by CHHORVORN
danielhanchen
updated 2
models 4 days ago
danielhanchen
published 2
models 4 days ago
danielhanchen
posted an update 5 days ago
Post
2793
1-bit GLM-5.2 GGUF vs. Claude 4.8 Opus vs. GPT-5.5
We gave 3 models the same prompt and compared one-shot outputs.
The 1-bit GLM-5.2 GGUF ran locally on a Mac Studio M3 Ultra with 256GB RAM at ~21.6 tok/s.
Which output do you like best?
GGUF: unsloth/GLM-5.2-GGUF
We gave 3 models the same prompt and compared one-shot outputs.
The 1-bit GLM-5.2 GGUF ran locally on a Mac Studio M3 Ultra with 256GB RAM at ~21.6 tok/s.
Which output do you like best?
GGUF: unsloth/GLM-5.2-GGUF
- 3 replies
danielhanchen
updated a
model 5 days ago
Jinja2 prompt template fix to get GLM5.2 running in LM Studio and Unsloth Studio
3
#6 opened 9 days ago
by 
Ackerka
Gibberish output IQ3_XXS
4
#4 opened 13 days ago
by 
AImhotep
danielhanchen
updated a
model 9 days ago
Cl/CL
1
#7 opened 12 days ago
by 
milezdeep13
GLM-5.2 GGUF Benchmarks!
❤️🔥 14
26
#3 opened 10 days ago
by danielhanchen
Is it possible to make less than 1 bit quantization?
🚀➕ 1
11
#1 opened 11 days ago
by 
RealBar
startup command please
👍 2
4
#2 opened 11 days ago
by 
mtcl