Qwen 3.8 Flash Next 176B-A6B · Chip comparison
Qwen 3.8 Flash Next 176B-A6B — GB300 NVL72 vs TPU7x
Head-to-head AI inference benchmark comparison of GB300 NVL72 (NVIDIA Blackwell) and TPU7x (Google Ironwood) on Qwen 3.8 Flash Next 176B-A6B. 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 →
At 124 tok/s/user on Qwen 3.8 Flash Next 176B-A6B, GB300 NVL72 delivers 186,162 tok/s/chip at $0.003 per million tokens; TPU7x hasn't been benchmarked at this target.
GB300 NVL72 hits 115,821 tok/s/chip for $0.006 per million tokens at 214 tok/s/user on Qwen 3.8 Flash Next 176B-A6B. No TPU7x data at this operating point.
GB300 NVL72: 75,399 tok/s/chip, $0.009 per million tokens at 304 tok/s/user on Qwen 3.8 Flash Next 176B-A6B. TPU7x is unmeasured here. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | GB300 NVL72186,162TPU7x— | GB300 NVL72115,821TPU7x— | GB300 NVL7275,399TPU7x— |
| Cost ($/M tok) | GB300 NVL72$0.003TPU7x— | GB300 NVL72$0.006TPU7x— | GB300 NVL72$0.009TPU7x— |
| tok/s/MW | GB300 NVL7287,812,451TPU7x— | GB300 NVL7254,632,428TPU7x— | GB300 NVL7235,565,694TPU7x— |
| Concurrency | GB300 NVL72~41TPU7x— | GB300 NVL72~20TPU7x— | GB300 NVL72~13TPU7x— |