NVIDIA
chat
Qwen 3 14B matches Chat and keeps a practical fit profile. It sits in the middle of the current generation mix. It fits natively with comfortable headroom. Context coverage stays within the requested workload envelope.
Decode 184.6 tok/s with ExLlamaV2.
coding
Qwen 2.5 Coder 32B is a specialized fit for Coding. It sits in the middle of the current generation mix. It fits natively with comfortable headroom. Context coverage stays within the requested workload envelope.
Decode 80.7 tok/s with ExLlamaV2.
reasoning
Qwen 2.5 32B matches Reasoning and keeps a practical fit profile. It sits in the middle of the current generation mix. It fits natively with comfortable headroom. Context coverage stays within the requested workload envelope.
Decode 80.7 tok/s with ExLlamaV2.