mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-10-29 08:41:22 +00:00
22 lines
526 B
Markdown
22 lines
526 B
Markdown
# perplexity
|
|
|
|
TODO
|
|
|
|
## Llama 2 70B Scorechart
|
|
Quantization | Model size (GiB) | Perplexity | Delta to fp16
|
|
-- | -- | -- | --
|
|
Q4_0 | 36.20 | 3.5550 | 3.61%
|
|
Q4_1 | 40.20 | 3.5125 | 2.37%
|
|
Q5_0 | 44.20 | 3.4744 | 1.26%
|
|
Q2_K | 27.27 | 3.7339 | 8.82%
|
|
Q3_K_S | 27.86 | 3.7019 | 7.89%
|
|
Q3_K_M | 30.83 | 3.5932 | 4.72%
|
|
Q3_K_L | 33.67 | 3.5617 | 3.80%
|
|
Q4_K_S | 36.39 | 3.4852 | 1.57%
|
|
Q4_K_M | 38.54 | 3.4725 | 1.20%
|
|
Q5_K_S | 44.20 | 3.4483 | 0.50%
|
|
Q5_K_M | 45.41 | 3.4451 | 0.40%
|
|
Q6_K | 52.70 | 3.4367 | 0.16%
|
|
fp16 | 128.5 | 3.4313 | -
|
|
|