Frontier model

DeepSeek V4 Flash: The one you actually deploy

284B total, 13B active, a million tokens of context, and a published serving recipe somebody else already tuned. The cheapest active-parameter count on this page.

MIT 284B total 13B active 1M context

The architecture

how it is built

The same attention as Pro

V4 Flash inherits the hybrid CSA and HCA design and the 1,048,576-token context window. It is not a distilled or truncated Pro, it is the same architecture at a smaller expert count.

13B active

The lowest active-parameter count of any model here, at full million-token context. This is the number that makes agent workloads, where a thousand sessions share a long system prompt, affordable rather than theoretical.

Mixed FP4 and FP8

Same checkpoint strategy as Pro: MoE expert parameters in FP4, most everything else in FP8. DeepSeek publishes the format but not a byte count, so the 150 GB figure below is derived and flagged as such wherever it appears. Worth noting the loaded model reports closer to 291B than the headline 284B, which is the sort of gap that turns a tight placement into an OOM.

Sampling defaults are not the usual ones

The card asks for temperature 1.0 and top_p 1.0, and for reasoning modes a context window of at least 384K. Carrying over a config tuned for a different model is how you get quality regressions that look like the model is worse than advertised.

Serving it

the playbook

The published vLLM recipe targets GB200, H200, B200 and B300 at TP=4 with DP=4, fp8 KV cache, block size 256, and gpu_memory_utilization at 0.92. A single-GPU DGX Station config exists at TP=1, PP=1 with 3-token MTP speculation and FULL_AND_PIECEWISE compilation.

On a 4,000-GPU HGX B200 fleet

500 nodes, eight B200s each, 180 GB per GPU
TP=2smallest placement that leaves a real cache budget
181 GBKV cache per replica, 55% of usable memory
4replicas per HGX node
2,000replicas across the fleet

Weights are 150 GB (FP4 experts + FP8 attention, derived). Usable memory is 180 GB x 0.92 per GPU, the gpu_memory_utilization from the published recipe. A placement only counts here if the cache gets at least 30% of what is left, because a config that fits the weights and nothing else cannot serve a request. Tensor parallel stays inside the NVSwitch, so no TP traffic ever crosses a NIC.

The one I would put in production

my read

Thirteen billion active parameters at a million tokens of context is the combination that makes agent workloads stop being a budget conversation. There is a published recipe somebody already tuned, which I value more than another point of benchmark score, and it runs on a single GPU if you need it to. My one caution is the derived weight figure below: I computed it from the published format rather than a byte count, so I would verify the real footprint against the checkpoint before committing a placement to it.

The numbers

measured elsewhere, not here
Total
284B
Active
13B
Output
135.2 tok/s
Output price
$1.32 / 1M

Throughput from Artificial Analysis on the 0731 reasoning, max-effort endpoint. GSM8K figure from the vLLM recipe on MI355X.

Sources: vLLM Recipes · Hugging Face: DeepSeek-V4-Flash · Artificial Analysis