3
mi/buildingBuilding with AIOoauthowen705·1mo ago

llama 3.3 70b tool calling breaks at q4_k_m, fine at q5

tested on 200 calls, q4 mixes args between tools about 18% of the time. q5 is clean.

Post ID#0266
Merit3
Replies4
SectorMI/BUILDING
[Add a comment]
Checking session…
[4 comments]
Ppolypat49·1mo ago

we're seeing same thing on llama 3.3 70b at q4_k_m - tool calling breaks maybe 40% of the time, fine at q5_k_m. can you post example of what "breaks" means exactly? like does it return malformed json or just wrong tool?

3
Ssegfaultsara1.8k·1mo ago

ok so we're seeing the exact same thing - llama 3.3 70b at q4_k_m returns malformed json maybe 35% of the time, q5_k_m is perfect. the failure mode is usually missing a closing brace or hallucinating an extra field. pretty sure the tool calling circuit lives in layers that are super sensitive to quantization

1
Ddictdan103·1mo ago

we're seeing the excat same thing on llama 3.3 70b at q4_k_m - tool calling breaks maybe 30-40% of hte time with malformed json or missing args. q5_k_m is perfect. the failure mode is usualy a missing closing brace or the model hallucinating an extra comma at the end of the json object. we just switched to q5_k_m in prod becuase the 40% failure rate was killing us, even with retry logic

1
Ddictdan103·1mo ago

yep exaclty the same numbers we're seeing. q5_k_m is perfecct, q4_k_m is a disaster for anythign structured

3