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). PrismML Bonsai Image 4B — a ternary-weight diffusion transformer built on the FLUX.2-klein-4B architecture — converted to LiteRT for on-device text-to-image. The whole pipeline runs in three fixed-shape `.tflite` graphs; the host does only tokenization, the FlowMatch-Euler loop, and latent unpatchify (`generate.py` in this repo, ~150 lines, no torch and no diffusers). Smallest working set: **3.97 GiB** (int4 text encoder). Output is 512×512 with the default pair of graphs, or 256×256 with the `dit_256` / `vae_dec_256` pair (`generate.py --size 256`; `variants.256` in `pipeline_meta.json`) — the text encoder, tokenizer and latent constants are shared by both sizes; 256 prompt tokens and 4 sampling steps by default (the model is step-distilled; more steps also work).

Image generation

Input Text→ Output Image

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

CLIPSeg-rd64-LiteRT

litert-community

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

Basic profile indexed · More details to follow

Image segmentation

Input Image→ Output Image

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

d1-3B-LiteRT

litert-community

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

Basic profile indexed · More details to follow

Text analysis

Input Text→ Output Text

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

COST EXPLORER

Great models. Clear costs.

Cost analysis

Adjust monthly token usage to compare estimated API costs.

Monthly input tokens 10 MMonthly output tokens 2 M1 M = 1 million tokens · USD
Compares base text-token rates within the same channel

Uses collected, comparable USD-per-million-token rates. Snapshots exclude cache discounts, tiers, extra reasoning output and taxes. Check current source prices.

MODEL HANDBOOK

Understand before you choose

Selection guide & FAQ

How should API prices be compared?+

Separate input, output and cache rates, then estimate the same workload. Image, audio and video rates may use items, duration or resolution rather than tokens.

Do open weights mean free commercial use?+

Not necessarily. Check each version’s license, commercial restrictions and policies. Self-hosting also incurs compute and maintenance costs.

Is the top-ranked model the best for me?+

Rankings depend on tasks, versions and methods. Compare accuracy, latency, reliability and costs on your own workload.

Find your ideal AI model.

Explore AI models 85001

Hermes-2-Pro-Llama-3-8B-GGUF

Hermes-2-Theta-Llama-3-8B-GGUF

Llama-3-8b-64k-PoSE-GGUF

Llama-3-8B-Instruct-Gradient-1048k-GGUF

Llama-3-8B-Web-GGUF

Llama-3-Open-Ko-8B-GGUF

Llama-3-Open-Ko-8B-Instruct-preview-GGUF

Llama-3-Smaug-8B-GGUF

Llama3-8B-Chinese-Chat-GGUF

Meta-Llama-3-13B-Instruct-GGUF

Meta-Llama-3-70B-Instruct-GGUF

Meta-Llama-3-8B-GGUF

Meta-Llama-3-8B-Instruct-GGUF

Mistral-7B-Instruct-v0.3-GGUF

Mistral-7B-Merge-14-v0.1-GGUF

Mixtral-8x22B-v0.1-GGUF

OGNO-7B-GGUF

OpenELM-1_1B-Instruct-GGUF

WizardLM-2-8x22B-GGUF

Agents-A1-4B

Audio8-TTS-Preview-0.6b

Bonsai-Image-ternary-4B

CLIPSeg-rd64-LiteRT

d1-3B-LiteRT

No matching models

Great models. Clear costs.

Understand before you choose

Follow trends. Find tools. Explore models.