I took a look and there are a wide array of different precisions in the "1-bit" quants. @danielhanchen , how can a "1-bit" model contain layers at Q8_0 and F32? Does 1-bit only refer to the quantization of the ffn* layers? In that case, what is the average precision of the entire "1-bit" model?
Michael
electrolanche
·
AI & ML interests
None yet
Recent Activity
repliedto danielhanchen's post about 14 hours ago
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: https://huggingface.co/unsloth/GLM-5.2-GGUF repliedto danielhanchen's post about 14 hours ago
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: https://huggingface.co/unsloth/GLM-5.2-GGUFOrganizations
None yet
replied to danielhanchen's post about 14 hours ago
replied to danielhanchen's post about 14 hours ago
Sample size n=1...
But seriously, it's impressive that a binary tree can output code that even executes. And at 1-bit there is no dynamic quantization (by definition), can't go lower than 1-bit!
What is the difference between this model and the original google/gemma-4-E4B-it?
👀 1
2
#1 opened about 1 month ago
by 
adel-cybral
replied to unmodeled-tyler's post 9 months ago
I’m curious to see how it compares against it’s base model, Qwen3 8B.
updated 3
collections over 1 year ago