[msluszniak]

Description

• Adds LFM 3 1.7B, LFM 3 VL 2B and LFM 3 Audio 2B (XNNPACK 8da4w, MLX int4/int8), 8K context.
• The multimodal runner accepts an audio_encoder model (LLM_AUDIO_SPEC) in place of vision_encoder.
• nlp app: LFM 3 entries, LFM 3 tool-call parser, hides the draft LFM 3 writes before </think> with thinking off.

Introduces a breaking change?

• Yes
• No

Type of change

• Bug fix (change which fixes an issue)
• New feature (change which adds functionality)
• Documentation update (improves or adds clarity to existing documentation)
• Other (chores, tests, code style improvements etc.)

Tested on

• iOS
• Android

Testing instructions

• nlp app, LLM screen: LFM 3 1.7B (chat, tool calling), LFM 3 VL 2B (image), LFM 3 Audio 2B (attach a WAV URL).

Screenshots

Related issues

Checklist

• I have performed a self-review of my code
• I have commented my code, particularly in hard-to-understand areas
• I have updated the documentation accordingly
• My changes generate no new warnings

Additional notes

• Vulkan variants follow separately; they need an ExecuTorch Vulkan SDPA fix in the libs.

[barhanc]

Suggested change

	const chunkSamples = Math.min(numSamples - offset, chunkStride);
	// Right-pad to window + k * hop samples, as the feature extractor does.
	const padded =
	chunkSamples <= window ? window : window + Math.ceil((chunkSamples - window) / hop) * hop;
	const numFrames = 1 + (padded - window) / hop;
	const numAudioTokens = Math.ceil(numFrames / framesPerToken);
	const chunkSamples = Math.min(numSamples - offset, chunkStride);
	// Right-pad to window + k * hop samples, as the feature extractor does.
	const k = Math.ceil((chunkSamples - window) / hop);
	const padded = chunkSamples <= window ? window : window + k * hop;
	const numFrames = 1 + (padded - window) / hop;
	const numAudioTokens = Math.ceil(numFrames / framesPerToken);

[barhanc]

I tested the new models in example app and they work great. I'm super impressed by the audio model---the prefill and decode speed and accuracy of the transcription are incredible (especially compared to Gemma) 🤯. I don't have iOS device to test the MLX versions so that will have to wait for tomorrow.

[msluszniak]

@kfaracik could you check the MLX and XNNPACK variants of these models on iOS since you have told me you have been adding these models.

[barhanc]

Ok, tested the MLX variants and they work just as well.

[kfaracik]

@kfaracik could you check the MLX and XNNPACK variants of these models on iOS since you have told me you have been adding these models.

Tested the XNNPACK 8da4w variants of LFM 3 1.7B and VL 2B on iOS and Android with the 0.11.0 legacy entry point. Both work. One catch: the legacy MultimodalPrefiller runs token_embedding over the whole prompt, and VL 2B's export bounds that input at 256 tokens, so longer prompts fail; we chunk it in a patch on our side.