Hugging Face's logo

PowerInfer
/
SmallThinker-21BA3B-Instruct

Text Generation
Safetensors
English
Model card Files Community
wdl339 commited on
Commit
0c1dea5
·
verified ·
1 Parent(s): 3abcff8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -28,9 +28,9 @@ For the MMLU evaluation, we use a 0-shot CoT setting.
28
  | Model | Memory(GiB) | i9 14900 | 1+13 8ge4 | rk3588 (16G) | Raspberry PI 5 |
29
  |--------------------------------------|---------------------|----------|-----------|--------------|----------------|
30
  | SmallThinker 21B+sparse | 11.47 | 30.19 | 23.03 | 10.84 | 6.61 |
31
- | SmallThinker 21B+sparse +limited memory | limit 8G | 20.30 | 15.50 | 8.56 | - |
32
  | Qwen3 30B A3B | 16.20 | 33.52 | 20.18 | 9.07 | - |
33
- | Qwen3 30B A3Blimited memory | limit 8G | 10.11 | 0.18 | 6.32 | - |
34
  | Gemma 3n E2B | 1G, theoretically | 36.88 | 27.06 | 12.50 | 6.66 |
35
  | Gemma 3n E4B | 2G, theoretically | 21.93 | 16.58 | 7.37 | 4.01 |
36
 
 
28
  | Model | Memory(GiB) | i9 14900 | 1+13 8ge4 | rk3588 (16G) | Raspberry PI 5 |
29
  |--------------------------------------|---------------------|----------|-----------|--------------|----------------|
30
  | SmallThinker 21B+sparse | 11.47 | 30.19 | 23.03 | 10.84 | 6.61 |
31
+ | SmallThinker 21B+sparse+limited memory | limit 8G | 20.30 | 15.50 | 8.56 | - |
32
  | Qwen3 30B A3B | 16.20 | 33.52 | 20.18 | 9.07 | - |
33
+ | Qwen3 30B A3B+limited memory | limit 8G | 10.11 | 0.18 | 6.32 | - |
34
  | Gemma 3n E2B | 1G, theoretically | 36.88 | 27.06 | 12.50 | 6.66 |
35
  | Gemma 3n E4B | 2G, theoretically | 21.93 | 16.58 | 7.37 | 4.01 |
36