Muse Spark 1.3/Open 816B · Chip comparison
Muse Spark 1.3/Open 816B — B300 vs MI355X
Head-to-head AI inference benchmark comparison of B300 (NVIDIA Blackwell) and MI355X (AMD CDNA 4) on Muse Spark 1.3/Open 816B. Latency, throughput, and cost across LLM workloads. Use the chart controls below to switch sequences, precisions, and metrics — same interactions as the main inference chart.
AgentX replays real coding-agent sessions rather than fixed-length prompts, so context grows turn over turn and most of each request is served from cache instead of being recomputed. That turns the comparison into a systems question: KV transfer between nodes, prefix-aware routing, and cache capacity all move the curve alongside raw chip throughput. Fixed-sequence workloads stay the clean baseline for kernel and silicon performance, so the two scenarios answer different questions about the same hardware. Learn more about AgentX →
Throughput at 179 tok/s/user on Muse Spark 1.3/Open 816B: B300 hits 27,488 tok/s/chip, MI355X hits 29,697. Costs per million tokens land at $0.023 and $0.014 respectively. MI355X is 39% cheaper per token; MI355X delivers 8% more tok/s/chip.
B300 / MI355X on Muse Spark 1.3/Open 816B at 286 tok/s/user: 16,588 / 14,190 tok/s/chip, $0.038 / $0.029 per million tokens. MI355X is 22% cheaper per token; B300 delivers 17% more tok/s/chip.
Toward the upper edge of the 73–500 tok/s/user interactivity band, at 393 tok/s/user on Muse Spark 1.3/Open 816B: B300 runs 10,745 tok/s/chip at $0.058 per million tokens, MI355X runs 7,825 at $0.053. MI355X is 9% cheaper per token; B300 delivers 37% more tok/s/chip. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B30027,488MI355X29,697 | B30016,588MI355X14,190 | B30010,745MI355X7,825 |
| Cost ($/M tok) | B300$0.023MI355X$0.014 | B300$0.038MI355X$0.029 | B300$0.058MI355X$0.053 |
| tok/s/MW | B30014,467,489MI355X14,209,024 | B3008,730,742MI355X6,789,623 | B3005,655,349MI355X3,743,987 |
| Concurrency | B300~18MI355X~28 | B300~19MI355X~22 | B300~13MI355X~9 |