13 Oct 2026
LFM2.5-24B-A2B
Active parameters are a compute clue, not a device budget
24B reported total · text
LFM / Convolution / sliding / full attention
Small weights can still carry a growing cache
New to model sizes or GPU memory? Start with weights, parameters and quantization →
Consider this checkpoint for constrained text workflows and local tool use. It is a deployment contrast to the large cluster models, not a claim of equivalent frontier reasoning quality.
Publisher-reported rounded count; the pinned tensor index is a separate payload measurement.
Evaluate it for
Task-specific local agents after evaluation on the intended tools and language.
Choose another path when
Complex coding or broad knowledge is the main requirement, or the license does not permit the intended use.
Release context
The 24-layer stack has 13 short convolutions, five sliding-attention layers and six full-attention layers. Only the local portions can stop growing with context.
Publisher release post; repository creation predates the announcement.
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.
Complex coding or broad knowledge is the main requirement, or the license does not permit the intended use.
The pinned model card establishes the architecture. It does not, by itself, prove that a particular GPU count runs this checkpoint at your target context. The capacity screen below helps rule out undersized allocations; a successful load and workload test are still required.
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.
| Representation | Approximate weight floor | What remains to budget |
|---|---|---|
| 16-bit uniform | 3.46 GB | Cache, modality state, workspace, quantization metadata and uneven sharding |
| 8-bit uniform | 1.73 GB | Cache, modality state, workspace, quantization metadata and uneven sharding |
| 4-bit uniform | 0.865 GB | Cache, modality state, workspace, quantization metadata and uneven sharding |
Enter the total across the whole model replica, not per GPU: KV or recurrent cache for all concurrent requests, image/audio state and execution workspace. There is no universal default. We additionally leave 15% of each GPU unused.
Enter a request-and-buffer budget to calculate the aggregate capacity requirement.
A count of one does not prove the engine supports this GPU. A count above one does not prove the model shards evenly or communicates efficiently. Publisher-reported rounded count; the pinned tensor index is a separate payload measurement.
Architecture in practice
Convolution history is not an attention KV array.
Global layers keep growing after local windows fill.
Mechanism schematic based on the pinned model card and configuration. It explains a design principle; it is not a full implementation graph.
| Exact checkpoint | LiquidAI/LFM3-1.7B |
|---|---|
| Text model type | lfm3 |
| Layers | 24 |
| Hidden width | 2,048 |
| Attention / KV heads | 16 / 4 |
| Head dimension | 128 |
| Routed / selected experts | Not verified / Not verified |
| Configured positions | 262,144 |
| Documented extension | Not recorded for this checkpoint |
| Inputs → output | text → text |
| License metadata | LFM Open License v1.0 · custom terms |
13 short convolution layers; 5 sliding attention layers; 6 full attention 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
The 24B sibling trades a larger expert store for a different capability and state profile. Compare task success and peak memory on the actual device.
13 Oct 2026
Active parameters are a compute clue, not a device budget
24B reported total · text
2 Mar 2026
A practical small-model starting point
4B 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
At two-byte KV, derive 2 KiB per attention-layer position. At 32,768 positions the six full layers alone retain 384 MiB before convolution state and runtime overhead.
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, “LFM3-1.7B: release, architecture and deployment”, checked 2026-11-16. Preserve this date and the exact checkpoint when citing.