Qwen 3.5 397B-A17B · B300 · Precision comparison
B300: FP8 vs BF16 precision comparison
How FP8 and BF16 precision affect Qwen 3.5 397B-A17B inference on B300 (NVIDIA Blackwell). Throughput, latency, and cost across LLM workloads. Use the chart controls below to switch sequences and metrics — same interactions as the main inference chart.
At 97 tok/s/user on Qwen 3.5 397B-A17B (B300), FP8 delivers 1,815 tok/s/chip at $0.35 per million tokens; BF16 delivers 1,475 tok/s/chip at $0.43. FP8 delivers 23% more tok/s/chip on the same chip, which makes it 19% cheaper per token. Lower-precision quantization trades model accuracy for throughput — check the evaluation page for quality impact.
FP8 posts 977 tok/s/chip for $0.64 per million tokens at 150 tok/s/user on Qwen 3.5 397B-A17B (B300); BF16 posts 774 tok/s/chip for $0.81. FP8 delivers 26% more tok/s/chip on the same chip, which makes it 21% cheaper per token. Quantization-level accuracy differences are tracked on the evaluation tab.
Throughput at 202 tok/s/user on Qwen 3.5 397B-A17B (B300): FP8 hits 662 tok/s/chip, BF16 hits 516. Costs per million tokens land at $0.95 and $1.22 respectively. FP8 delivers 28% more tok/s/chip on the same chip, which makes it 22% cheaper per token. The cost-throughput tradeoff from lower precision is only part of the picture — see the evaluation page for accuracy data. (Numbers reflect the default 1k/1k selection for this URL — table and chart below update if you change sequence or model in the controls. Each side uses the best available serving configuration for that precision, which may include speculative decoding such as MTP where recipes exist — the same convention as the other comparison pages.)
Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | FP81,815BF161,475 | FP8977BF16774 | FP8662BF16516 |
| Cost ($/M tok) | FP8$0.35BF16$0.43 | FP8$0.64BF16$0.81 | FP8$0.95BF16$1.22 |
| tok/s/MW | FP8955,439BF16776,371 | FP8514,418BF16407,248 | FP8348,185BF16271,799 |
| Concurrency | FP8~39BF16~64 | FP8~14BF16~22 | FP8~7BF16~8 |
