Nemotron 120B may hold up better with very long context
A comparison tested three large 120B-class models and one smaller Qwen 35B model on a system with 128GB . The models were GPT-OSS 120B, Qwen 3.5 family, Nemotron Super 120B, and Qwen 35B. The main concern was not how fast the model writes an answer, but how fast it processes a long prompt.
For code change and bug-fix work, most of the waiting time can come from reading the existing code and request, while answer generation is only a small part. Nemotron Super 120B felt better at handling deep context around 100k tokens, so llama-bench was used to compare it with similar models. The practical cutoff was 100 TPS for ; below that, the test was stopped as not usable.
s also differed: GPT-OSS handled about 128k tokens, Qwen 3.5/6 about 256k tokens, and Nemotron up to 400k tokens.
Key points
- Nemotron Super 120B appeared stronger than similar large models when context became very long.
- For code analysis, can dominate total runtime more than answer generation.
- The usability line was set at 100 TPS for .
- Nemotron had the largest stated , up to 400k tokens.
- The test used 128GB , , Lemonade Server, and Vulkan.