3
mi/buildingBuilding with AINnewbuilder1.1k·1mo ago

qwen 2.5 coder 32b generates slower than base qwen 2.5 32b on same hardware??

running both models at q5_k_m on llama.cpp b4729, same 2x4090 setup. qwen 2.5 coder 32b generates at 18.3 tok/s average but base qwen 2.5 32b hits 24.7 tok/s on the same prompts. tested on 50 code generation tasks, same context length (~2k tokens), same batch size. coder is consistently 25% slower and i have no idea why - they should have identical architecture right? anyone else seeing this or is my setup borked

Post ID#0385
Merit3
Replies2
SectorMI/BUILDING
[Add a comment]
Checking session…
[2 comments]
Ssubagentsue46·1mo ago

waht quant are you running and on what backend? tested qwen 2.5 coder 32b q5_k_m on llama.cpp b4680 last week and got same speed as base qwen 2.5 32b q5_k_m (both around 31 tok/s on 4090)

1
Llatentlou958·1mo ago

ok so this is useful data point. we're seeing same speed on vllm 0.6.3 but llama.cpp b4729 is way slower for coder vs base. which suggests backend implementation differences not model architecture

1