Runtime recipe
8 × H200 SXM
141 GB per GPU
SGLang dev-ling-3.1-flash image
Publisher command uses TP8, EP8 and NEXTN speculation. It does not establish useful concurrency at the advertised maximum context.
Ling / Hybrid KDA / gated MLA MoE
Count recurrent and latent state separately
New to model sizes or GPU memory? Start with weights, parameters and quantization →
A cluster candidate for text agents when its task quality justifies the expert store. Its smaller active path reduces computation without making all weights disappear.
Publisher-reported rounded count; the pinned tensor index is a separate payload measurement.
Evaluate it for
Text-agent evaluation with a runtime that supports this exact hybrid layout.
Choose another path when
A workstation budget, image inputs, or a requirement for already-qualified million-token concurrency.
Release context
Sixty-three Kimi Delta Attention layers retain recurrent state; nine gated multi-head latent-attention layers retain history. Cache reuse must restore both.
Dated weight-upload commit; not inferred from repository creation or an API listing.
Deployment starting points
Start with an exact artifact and an engine that supports it. A configuration below is evidence of a documented path; its device count does not promise a particular throughput or concurrency.
Runtime recipe
141 GB per GPU
SGLang dev-ling-3.1-flash image
Publisher command uses TP8, EP8 and NEXTN speculation. It does not establish useful concurrency at the advertised maximum context.
This is the index’s reported tensor payload, in decimal GB. It excludes file headers and runtime memory. Mixed precision, conversion and host/device placement determine how much GPU memory the loaded model needs.
Inspect the exact index metadata →This estimates inference memory for a hypothetical uniform precision. It is useful for rejecting an allocation that is too small. It does not establish a working deployment or estimate training memory.
A uniform-precision GPU count would hide this model’s component layout. Publisher-reported rounded count; the pinned tensor index is a separate payload measurement. Use the documented artifact and placement path above; no GPU count is inferred here.
Architecture in practice
Hybrid attention does not mean zero request state.
A full-attention formula cannot describe every layer.
Mechanism schematic based on the pinned model card and configuration. It explains a design principle; it is not a full implementation graph.
| Exact checkpoint | inclusionAI/Ling-3.1-flash |
|---|---|
| Text model type | bailing_hybrid |
| Layers | 72 |
| Hidden width | 4,096 |
| Attention / KV heads | 64 / 64 |
| Head dimension | Not verified |
| Routed / selected experts | 512 / 8 |
| Configured positions | 262,144 |
| Documented extension | Not recorded for this checkpoint |
| Inputs → output | text → text |
| License metadata | apache-2.0 |
63 KDA layers; 9 gated MLA layers. These counts describe the configured pattern.
Open weights do not imply unrestricted use. Read the applicable license terms linked from the pinned card.
A useful comparison
Compare the two Ling revisions under one harness. The smaller alternative changes residency costs as well as possible task quality.
27 Oct 2026
A post-training update needs its own deployment evidence
560B reported total · text
23 Oct 2026
M3 with sparse attention everywhere and a quantized-trained store
428B reported total · text + image + video
These are editorial comparison candidates. We have not run a matched quality or serving benchmark, so this is not a ranking.
Prepare to explain it
Budget the 573.75 GB tensor payload separately from recurrent snapshots and the nine latent caches.
Attention layouts · Quantization · Courses and worked examples
For a deployment evaluation, record exact weights, precision, engine, device count, interconnect, prompt/output lengths and concurrency. Report task success, errors, TTFT, TPOT and useful throughput together.
Our assessment is editorial judgment based on the linked architecture and deployment evidence. Model facts are publisher-reported or attributed to runtime maintainers; no independent GPU benchmark was run.
AI Infra Interviews, “Ling-3.1-flash: release, architecture and deployment”, checked 2026-11-16. Preserve this date and the exact checkpoint when citing.