All model and GPU pairings
Qwen 3.8 Flash Next 176B-A6BNVIDIA Blackwell

Running Qwen3.8-Flash-Next on B300

Quick answer

Qwen3.8-Flash-Next runs on B300: 5 benchmarked configs so far. See the interactivity ladder below for measured operating points.

Benchmarked configs

5

Serving engines

SGLang

Precisions

fp4

Run dates

2026-08-272026-08-27

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 targetTokens/s per GPU$ / 1M tokensEnginePrecision
30 tok/s--SGLangfp4
50 tok/s--SGLangfp4
75 tok/s--SGLangfp4
100 tok/s72,091$0.009SGLangfp4
150 tok/s47,295$0.013SGLangfp4
200 tok/s--SGLangfp4

Frequently asked questions

How fast is Qwen3.8-Flash-Next on B300?
The InferenceX fleet has 5 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 B300?
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 B300?
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 B300 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 2026-08-27. The same derivation powers the InferenceX overview leaderboard.

Explore the data