NInfer on the NVIDIA RTX Pro 6000 Blackwell
On the NVIDIA RTX Pro 6000 Blackwell, NInfer runs Qwen3.8 125B · 6B active at 4-bit at a median 172.0 tokens per second for generation, from 1 plain run (512 context).
Speed by model on the NVIDIA RTX Pro 6000 Blackwell
Plain runs only: one device, one request, no speculative decoding, the whole model in memory. Each row is one model size at one bit class, with the other engines' plain runs of the same model on this card beside it. Context length and build still differ between runs, and each side shows its own.
| Model | NInfer | Other engines |
|---|---|---|
| Qwen3.8 125B · 6B active 4-bit | 172.0 t/sone report, 512 context | llama.cpp 105.5 t/smedian of 2, 2K to 240K context ik_llama.cpp 40.0 t/sone report, 200K context |
3 NInfer reports on the NVIDIA RTX Pro 6000 Blackwell
Newest first. A run on several cards, with speculative decoding, with part of the model in system RAM or with batched requests says so, since each describes a different setup.
- Qwen3.8 125B · 6B active · NVFP4172.0 t/s
- Qwen3.6 35B · 3B active600.0 t/s
- Qwen3.8 27B · groupwise-int104.8 t/s
Frequently asked
How fast is NInfer on the NVIDIA RTX Pro 6000 Blackwell?
On the NVIDIA RTX Pro 6000 Blackwell, NInfer runs Qwen3.8 125B · 6B active at 4-bit at a median 172.0 tokens per second for generation, from 1 plain run (512 context).
Is NInfer faster than other engines on the NVIDIA RTX Pro 6000 Blackwell?
Same card, same model size and bit class, plain runs only: Qwen3.8 125B · 6B active at 4-bit gives NInfer 172.0 t/s (1 run) and llama.cpp 105.5 t/s (2), ik_llama.cpp 40.0 t/s (1). Context length and engine build differ between the runs, so treat it as a lead, not a benchmark.