Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Language Modeling on Mistral-7B Long-context (4k window)
Loading...
5.241
Perplexity
fp16
5.18452
5.56576
5.947
6.32824
May 26, 2026
Perplexity
Updated 1mo ago
Evaluation Results
Method
Method
Links
Perplexity
fp16
bits=16.00, evaluation...
2026.05
5.241
hqmq_s192_r4
bits=4.04, evaluation...
2026.05
5.273
hqmq_s192_r6
bits=4.54, evaluation...
2026.05
5.277
naive int4
bits=4.00, evaluation...
2026.05
5.331
hqmq_s96_r4
bits=3.79, evaluation...
2026.05
5.332
hqmq_s24_r4
bits=3.29, evaluation...
2026.05
5.442
hqmq_s24_r3
bits=3.04, evaluation...
2026.05
5.532
naive int3
bits=3.00, evaluation...
2026.05
6.653
Feedback
Search any
task
Search any
task