Qwen
/

Qwen3-32B-AWQ

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions

feihu.hf commited on May 8

Commit

c104c98

·

1 Parent(s): 7582e9d

update README

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -319,8 +319,8 @@ YaRN is currently supported by several inference frameworks, e.g., `transformers
 ## Performance
 | Mode | QUANTIZATION TYPE | LiveBench 2024-11-25 | GPQA | MMLU-Redux | AIME24 |
-| --- | --- | --- |
-| Thinking | bf16 | 74.7 | 68.4 | 90.9 | 81.4 |
 | Thinking | AWQ-int4 | 73.1 | 69.0 | 90.8 | 79.4 |
 | Non-Thinking | bf16 | 59.8 | 54.6 | 85.7 | - |
 | Non-Thinking | AWQ-int4 | 59.8 | 53.1 | 85.6 | - |

 ## Performance
 | Mode | QUANTIZATION TYPE | LiveBench 2024-11-25 | GPQA | MMLU-Redux | AIME24 |
+| --- | --- | --- | --- | --- | --- |
+| Thinking | bf16 | 74.9 | 68.4 | 90.9 | 81.4 |
 | Thinking | AWQ-int4 | 73.1 | 69.0 | 90.8 | 79.4 |
 | Non-Thinking | bf16 | 59.8 | 54.6 | 85.7 | - |
 | Non-Thinking | AWQ-int4 | 59.8 | 53.1 | 85.6 | - |