v0.33.3: gemma4: image and audio input support
Artikelbild eller återanvändbart omslag för Ollama
Safetensors gemma4 imports served by the MLX engine now answer image and audio chats.
Images run through both vision architectures: the transformer tower (26B, 31B, e-series) and the 12B's encoder-free unified embedder. Audio arrives through the same intake the ollama API already accepts for gemma4 GGUFs — WAV bytes in the images field, OpenAI input_audio parts, and /v1/audio/transcriptions uploads — with the e2b/e4b checkpoints running clips through their conformer audio encoder and the 12b unified checkpoint embedding the raw waveform directly. Clips longer than 30 seconds are split evenly into chunks of at most 30 seconds, cut at pauses, and encoded independently. Each modality serves only checkpoints that carry it: 26B/31B have no audio config and reject audio input, and checkpoints with an unrecognized vision architecture still load as text-only models and reject image requests. The server previously hid the vision and audio capabilities for gemma4 safetensors because the engine served neither. Both suppressions are removed, and existing imports start advertising the capabilities without re-importing since import already records them.
Texten är källans egen beskrivning av publiceringen. Innehållet tillhör Ollama.
Mer från Ollama
v0.40.11
Ollama 24 okt.
v0.40.11: voice: add voice catalog for Phonon (#19242)
Ollama 24 okt.
Outside of tech there has been no financial payoff to US companies for using AI, now viewed as a margin-hurting cost center, as VC-backed firms burn more tokens
Techmeme för 3 tim sedan
Source: Replit recently moved most AI spend from Anthropic to OpenAI, which gave 30%+ off in a deal worth $100M+/year, after Anthropic discontinued its discount
Techmeme för 5 tim sedan