Kimi K3 2.8T · Chip comparison
Kimi K3 2.8T — B300 vs GB300 NVL72
Head-to-head AI inference benchmark comparison of B300 (NVIDIA Blackwell) and GB300 NVL72 (NVIDIA Blackwell) on Kimi K3 2.8T. 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 →
B300 / GB300 NVL72 on Kimi K3 2.8T at 76 tok/s/user: 4,615 / 17,858 tok/s/chip, $0.14 / $0.036 per million tokens. GB300 NVL72 is 74% cheaper per token; GB300 NVL72 delivers 3.9× the tok/s/chip.
Around the middle of the 35–202 tok/s/user interactivity band, at 119 tok/s/user on Kimi K3 2.8T: B300 runs 3,262 tok/s/chip at $0.19 per million tokens, GB300 NVL72 runs 11,096 at $0.058. GB300 NVL72 is 70% cheaper per token; GB300 NVL72 delivers 3.4× the tok/s/chip.
Setting 161 tok/s/user as the target on Kimi K3 2.8T, B300 produces 2,059 tok/s/chip ($0.30 per million tokens) and GB300 NVL72 produces 9,833 ($0.065). GB300 NVL72 is 79% cheaper per token; GB300 NVL72 delivers 4.8× the tok/s/chip. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
GB300 NVL72 vs B300: full specs & benchmarks across models →
Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B3004,615GB300 NVL7217,858 | B3003,262GB300 NVL7211,096 | B3002,059GB300 NVL729,833 |
| Cost ($/M tok) | B300$0.14GB300 NVL72$0.036 | B300$0.19GB300 NVL72$0.058 | B300$0.30GB300 NVL72$0.065 |
| tok/s/MW | B3002,429,185GB300 NVL728,423,721 | B3001,716,614GB300 NVL725,234,048 | B3001,083,881GB300 NVL724,638,248 |
| Concurrency | B300~7GB300 NVL72~171 | B300~4GB300 NVL72~43 | B300~1GB300 NVL72~33 |