01Measured result
Ornith 397B
1× Nvidia RTX PRO 6000
96 GB VRAM · 200 GB DDR4
2,354tokens/secPrefill
25.72tokens/secDecode
Technical workMeasured, then explained
Results before adjectives.
We publish measured work so you can see what the products do and how we think. The first set covers large-model inference with Krasis.
Krasis / Benchmarks
Large models on single-GPU systems.
These results show three models running with Krasis. They are individual demonstrations on different systems, not a direct ranking between models or graphics cards.
02Measured result
Step 3.7
1× Nvidia RTX PRO 6000
Single-GPU system
5,261tokens/secPrefill
55.4tokens/secDecode
03Measured result
Qwen 3.5 122B
1× Nvidia RTX 5090
Single-GPU system
3,692tokens/secPrefill
31.8tokens/secDecode
Reading the results
01
Prefill
Prefill is the work of reading and processing the input before a response begins. Faster prefill matters when prompts and context are large.
02
Decode
Decode is the generation of the response itself. Its token rate is the speed a person experiences once the model starts answering.
03
Reproducibility
Model configuration, prompt length and software versions affect results. Full test details will be published alongside future engineering notes.
Your system
Unsure where the bottleneck is?
Northloom offers focused, remote reviews of self-hosted inference systems and proposed hardware designs.
Ask an inference question