Qwen 3.8 Flash Next 176B-A6BNVIDIA Blackwell
Running Qwen3.8-Flash-Next on B200
Quick answer
Qwen3.8-Flash-Next runs on B200: 4 benchmarked configs so far. See the interactivity ladder below for measured operating points.
Benchmarked configs
4
Serving engines
SGLang
Precisions
fp4
Run dates
2026-09-15 → 2026-09-15
Throughput at every interactivity target
Serving is a trade-off: push more concurrent users through a GPU and each user's tokens arrive slower. The ladder below reads the measured frontier at each per-user speed target on the AgentX agentic coding workload, using the best engine and precision at that point.
| Per-user target | Tokens/s per GPU | $ / 1M tokens | Engine | Precision |
|---|---|---|---|---|
| 30 tok/s | - | - | SGLang | fp4 |
| 50 tok/s | - | - | SGLang | fp4 |
| 75 tok/s | 65,052 | $0.007 | SGLang | fp4 |
| 100 tok/s | 57,615 | $0.008 | SGLang | fp4 |
| 150 tok/s | 38,489 | $0.012 | SGLang | fp4 |
| 200 tok/s | 19,592 | $0.025 | SGLang | fp4 |
Frequently asked questions
- How fast is Qwen3.8-Flash-Next on B200?
- The InferenceX fleet has 4 benchmarked configs for this pairing; see the interactivity ladder above for the operating points reached so far.
- How much does it cost to serve Qwen3.8-Flash-Next on B200?
- Cost per million tokens is derived from measured throughput and $/GPU/hr rates from the SemiAnalysis AI Cloud TCO model; it appears once this pairing reaches the primary interactivity tier.
- Which serving engines run Qwen3.8-Flash-Next on B200?
- The runs behind this page used SGLang in FP4. Engines are rebuilt and re-benchmarked continuously, so the best config can change between visits.
- How are these Qwen3.8-Flash-Next numbers measured?
- Every number is measured on real B200 hardware by the InferenceX fleet, sweeping concurrency on the AgentX agentic coding workload to trace the throughput-versus-interactivity frontier; the newest run landed on 2026-09-15. The same derivation powers the InferenceX overview leaderboard.