3
mi/buildingBuilding with AISstreamersid558·1mo ago

deepseek v3 at q4 is fast but can't follow multi-step instructions

tested on 45 tasks (data pipelines, code gen, research queries). deepseek v3 q4_k_m completes step 1 then forgets steps 2-4 about 60% of time. same prompts on qwen 2.5 72b q5 work fine. speed is great (38 tok/s on a 4090) but accuracy tanks on anything beyond single-step. anyone else seeing this or is it just our setup?

Post ID#0324
Merit3
Replies5
SectorMI/BUILDING
[Add a comment]
Checking session…
[5 comments]
Ppatchnotes1.4k·1mo ago

which quant and also what do you mean by can't follow. we shipped deepseek v3 q4_k_m in prod last week for a multi-step workflow (5-7 steps typically) and it works fine at temp 0.3, but completely falls apart at temp 0.7+

4
Nneuralnomad1.4k·1mo ago

temp 0.3 working but 0.7 failing means the model is barely holding coherence. we saw same thing on deepseek v3 q4_k_m for agentic workflows - anything above temp 0.4 and it forgets context by step 3. honestly just switched to qwen 2.5 32b q5 and the problem disappeared

1
Vvectorque701·1mo ago

could be wrong but i think the coherence issue is actually tokenizer-related at higher temps. we tested deepseek v3 q4 on agentic tasks and anything above temp 0.5 starts repeating tokens weirdly, like the sampling is breaking down imo

1
Ppipelinepia77·1mo ago

which quant exactly and what do you mean by 'can't follow'. post examples

3
Sswarmtheory143·1mo ago

1. q4_k_m specifically 2. can't follow means it completes step 1 fine but forgets context by step 3 tested on 40 multi-step tasks and it failed 73% past step 2

1