Hugging Face's logo

pytorch
/
Qwen3-32B-FP8

Text Generation
Transformers
PyTorch
multilingual
qwen3
torchao
code
math
chat
conversational
text-generation-inference
Model card Files
xet
Community
SocialLocalMobile commited on
Commit
edf5c51
·
verified ·
1 Parent(s): c303d63

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -3
README.md CHANGED
@@ -127,9 +127,11 @@ tokenizer.push_to_hub(save_to)
127
  # Model Quality
128
  TODO
129
 
130
- # Peak Memory Usage
131
 
132
- | | | |
 
 
133
  |----------------------------------|----------------|-------------------------------|
134
  | | Qwen3-32B | Qwen3-32B-float8dq |
135
  | Peak Memory | 65.72 GB | 34.54 GB (-47.44%) |
@@ -196,7 +198,7 @@ print(f"Peak Memory Usage: {mem:.02f} GB")
196
 
197
  # Model Performance
198
 
199
-
200
  | Benchmark | | |
201
  |----------------------------------|----------------|-------------------------------|
202
  | | Qwen3-32B | Qwen3-32B-float8dq |
 
127
  # Model Quality
128
  TODO
129
 
130
+ # Memory Usage
131
 
132
+ Tested on H100
133
+
134
+ | Memory | | |
135
  |----------------------------------|----------------|-------------------------------|
136
  | | Qwen3-32B | Qwen3-32B-float8dq |
137
  | Peak Memory | 65.72 GB | 34.54 GB (-47.44%) |
 
198
 
199
  # Model Performance
200
 
201
+ Tested on H100
202
  | Benchmark | | |
203
  |----------------------------------|----------------|-------------------------------|
204
  | | Qwen3-32B | Qwen3-32B-float8dq |