DeepSeek V4.1 Flash 552BNVIDIA Blackwell
Running DeepSeek V4.1 Flash on GB300 NVL72
Quick answer
DeepSeek V4.1 Flash runs on GB300 NVL72: 8 benchmarked configs so far. See the interactivity ladder below for measured operating points.
Benchmarked configs
8
Serving engines
vLLM
Precisions
fp4
Run dates
2026-09-11 → 2026-09-11
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 | - | - | vLLM | fp4 |
| 50 tok/s | - | - | vLLM | fp4 |
| 75 tok/s | - | - | vLLM | fp4 |
| 100 tok/s | - | - | vLLM | fp4 |
| 150 tok/s | - | - | vLLM | fp4 |
| 200 tok/s | - | - | vLLM | fp4 |
Frequently asked questions
- How fast is DeepSeek V4.1 Flash on GB300 NVL72?
- The InferenceX fleet has 8 benchmarked configs for this pairing; see the interactivity ladder above for the operating points reached so far.
- How much does it cost to serve DeepSeek V4.1 Flash on GB300 NVL72?
- 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 DeepSeek V4.1 Flash on GB300 NVL72?
- The runs behind this page used vLLM in FP4. Engines are rebuilt and re-benchmarked continuously, so the best config can change between visits.
- How are these DeepSeek V4.1 Flash numbers measured?
- Every number is measured on real GB300 NVL72 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 2026-09-11. The same derivation powers the InferenceX overview leaderboard.