MODEL PROFILE

LFM2.5-1.2B-Instruct

litert-community · LFM2.5-1.2B-Instruct

LiteRT is Google's on-device runtime, the new name for TensorFlow Lite (Android: `com.google.ai.edge.litert:litert`), and `litert-torch`, the renamed `ai-edge-torch`, is its PyTorch converter: a PyTorch model converted unmodified with `litert_torch.convert` matched the original to 4e-7 on a Galaxy S26 (measured, LiteRT 2.2.0, Android 16, 2026-09-05). Measured on device (edge-compat, lfm2.5-1.2b-instruct-int4): Galaxy S26 · LiteRT-LM 0.16.0 · GPU · did not run: engine_create_failed (2026-08-23); Raspberry Pi 5 · LiteRT-LM 0.16.1 · CPU, 4 threads · decode 9.3 tok/s · prefill 54 tok/s · TTFT 4.84 s (2026-09-01). Record: https://github.com/john-rocky/edge-compat/blob/main/cards/lfm2.5-1.2b-instruct-int4/CARD.md Measured on device (edge-compat, lfm2.5-1.2b-instruct-int8): Galaxy S26 · LiteRT-LM 0.16.0 · CPU · decode 41.0 tok/s · prefill 491 tok/s · TTFT 440 ms (2026-09-05); Pixel 8a · LiteRT-LM 0.16.0 · CPU · decode 20.4 tok/s · prefill 143 tok/s · TTFT 1.48 s (2026-09-05); Raspberry Pi 5 · LiteRT-LM 0.16.1 · CPU, 4 threads · decode 7.0 tok/s · prefill 75 tok/s · TTFT 3.56 s (2026-09-01). Record: https://github.com/john-rocky/edge-compat/blob/main/cards/lfm2.5-1.2b-instruct-int8/CARD.md

Text generationlicense:other
Context windowNot disclosed
Input → OutputText → Text
Model weightsNot verified
Profile updated2026/10/31 04:17:53
OVERVIEW

Model overview

LiteRT is Google's on-device runtime, the new name for TensorFlow Lite (Android: `com.google.ai.edge.litert:litert`), and `litert-torch`, the renamed `ai-edge-torch`, is its PyTorch converter: a PyTorch model converted unmodified with `litert_torch.convert` matched the original to 4e-7 on a Galaxy S26 (measured, LiteRT 2.2.0, Android 16, 2026-09-05). Measured on device (edge-compat, lfm2.5-1.2b-instruct-int4): Galaxy S26 · LiteRT-LM 0.16.0 · GPU · did not run: engine_create_failed (2026-08-23); Raspberry Pi 5 · LiteRT-LM 0.16.1 · CPU, 4 threads · decode 9.3 tok/s · prefill 54 tok/s · TTFT 4.84 s (2026-09-01). Record: https://github.com/john-rocky/edge-compat/blob/main/cards/lfm2.5-1.2b-instruct-int4/CARD.md Measured on device (edge-compat, lfm2.5-1.2b-instruct-int8): Galaxy S26 · LiteRT-LM 0.16.0 · CPU · decode 41.0 tok/s · prefill 491 tok/s · TTFT 440 ms (2026-09-05); Pixel 8a · LiteRT-LM 0.16.0 · CPU · decode 20.4 tok/s · prefill 143 tok/s · TTFT 1.48 s (2026-09-05); Raspberry Pi 5 · LiteRT-LM 0.16.1 · CPU, 4 threads · decode 7.0 tok/s · prefill 75 tok/s · TTFT 3.56 s (2026-09-01). Record: https://github.com/john-rocky/edge-compat/blob/main/cards/lfm2.5-1.2b-instruct-int8/CARD.md

Key features

特点摘要待依据来源补齐,不凭模型名称推断能力。

Limitations & considerations

Sources are insufficient to establish specific limitations. Verify task performance, latency, data policies, licensing and version lifecycle.

PRICING & COST

Source prices & cost analysis

Prices vary by channel, region and configuration. Channel quotes are listed independently and are not treated as a single official provider price.

Source / channelInputOutputBilling unitCollected at
No verified prices yet. Check the source channel.

Estimate monthly base token costs

—

Estimates exclude cache discounts, tiered pricing, multimodal surcharges, web search, taxes and additional reasoning output.

INDEPENDENT BENCHMARKS

Public benchmarks & run configuration

暂无已采集的可核验公开评分。模型未上榜不代表能力较低。

View full indexed rankings →

Frequently asked questions

Do open weights permit free commercial use?

Not necessarily. Check the version license, commercial conditions and usage policies. Self-hosting incurs compute and maintenance costs.

Are these real-time billing prices?

These are timestamped source snapshots, not live billing prices. Check the channel for current versions, regions, discounts and billing methods.

Sources & traceability

许可证:other。模型介绍与第三方评测均以原来源的具体版本和方法为准。