MoE deployment shortlist
Compare open-weight MoE candidates using total and active parameter scope, with clear notes on sparse computation, full weight storage, and distributed serving.
- What is included
- Seven selected MoE profiles with total and active parameter figures recorded in the directory. The counts have different publisher boundaries and are not normalized compute or memory measurements.
- How this list is ordered
- Alphabetical by model name. Active-to-total ratios are not used as an efficiency ranking.
Publisher sources are linked for every model. No independent performance scores have been measured. On smaller screens, scroll the table horizontally.
| Model | Total / active | Context | Deployment note |
|---|---|---|---|
| ~26B / 3.8B | 256K | The language backbone and vision encoder have distinct parameter scope.Compare model | |
| 309B+ / 15B | 1M | The backbone count excludes additional multimodal and prediction modules.Compare model | |
| ~428B / 23B | 1M | Sparse attention and expert routing both need compatible runtime support.Compare model | |
| 119B / 6.5B | 256K | Use the total checkpoint scope, not the Small name or active count, for sizing.Compare model | |
| 30B / 3B | 1M | The listed checkpoint uses NVFP4; stored and compute precision can differ.Compare model | |
| 80B / 3B | 256K | 3B active does not turn the full 80B checkpoint into a 3B memory budget.Compare model | |
| 125B+ / 6B | 256K native | Additional n-gram embeddings and the prediction head matter for total storage.Compare model |
A sparse compute count is not a resident weight count
Experts that are unused for one token can still occupy memory in a fully resident deployment. Total and active parameters belong in separate columns. Offloading changes where weights are held and how they are transferred, so it should have its own measured configuration rather than borrowing a fully resident result.
Do not rank efficiency from a ratio
An active-to-total ratio omits architectural work, memory traffic, communication, and runtime implementation. Two models with similar ratios may have very different serving requirements. This page intentionally exposes the source numbers without converting them into a quality or speed score.
Measure the system you plan to rent
For distributed configurations, record GPU count, interconnect, parallelism, precision, and request load. Test whether your latency target holds while the service processes realistic inputs. Until those runs are complete, the table is a deployment planning aid and not a recommendation for a particular instance type.
Before you choose hardware
MoE GPU requirements: active parameters vs. total weights explains the next planning step. For the distinction between publisher specifications, calculations, and measurements, read the BenchGrid methodology.