Downloads · 30 days
0
gemma-4-12B-it-coreai
warshanks/gemma-4-12B-it-coreai
gemma-4-12B-it-coreai is a image-text-to-text model from warshanks. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
google/gemma-4-12B-it converted to Apple's Core AI format (macOS 27 / iOS 27, WWDC 2026) with INT4 (block-32, weight-only) quantization of the decoder. Runs on Apple Silicon GPU via CoreAI.framework.
Access
Public
Updated Jun 12, 2026
Repo size
27.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.mlirb6.8 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- License
- apache-2.0
- Access
- Public
- Created
- Jun 11, 2026
- Updated
- Jun 12, 2026
- SHA
- 022fa7c2
Try a prompt
Base models
Model card
From the Hugging Face model README
Gemma 4 12B IT — Core AI (.aimodel), 4-bit, multimodal
google/gemma-4-12B-it converted to Apple's
Core AI format (macOS 27 / iOS 27, WWDC 2026) with INT4 (block-32, weight-only)
quantization of the decoder. Runs on Apple Silicon GPU via CoreAI.framework.
This is, to our knowledge, the first Gemma 4 conversion for Core AI. The
gemma4_unified architecture (interleaved sliding/global attention with K==V
global MQA, proportional partial RoPE, encoder-free multimodality) is not yet
covered by Apple's coreai-models
recipes; the conversion recipe used here is a custom extension of that toolkit.
Bundle contents
gemma_4_12b_it_mm_4bit.aimodel | multi-function Core AI asset (~6.4 GB) |
tokenizer/ | HF tokenizer + chat template |
metadata.json | bundle metadata (0.2 schema) + multimodal constants |
Functions
| Function | Inputs | Output | Purpose |
|---|---|---|---|
main | input_ids, position_ids (+ keyCache/valueCache states) | logits | text prefill + decode (causal, built-in sliding window) |
prefill_multimodal | input_ids, mm_embeds, mm_mask, position_ids, mask_sliding, mask_global (+ KV states) | logits | multimodal prefill; text embedding lookup happens in-graph, multimodal embeddings spliced via mm_mask |
embed_vision | pixel_values [1,P,6912], image_position_ids [1,P,2] | embeds [1,P,3840] | encoder-free image/video-frame embedder (48×48×3 merged patches) |
embed_audio | input_features [1,T,640] | embeds [1,T,3840] | raw 16 kHz audio frames (640 samples per token) |
Attention masks are boolean (True = attend); a provided mask fully
overrides the built-in causal/sliding-window behavior, so the multimodal
prefill masks must encode causality + the 1024-token sliding window + the
bidirectional attention within each image/video token block
(mm_token_type_ids 1/2), mirroring HF Gemma4UnifiedModel.
Multimodal token constants (also in metadata.json): image 258880, audio
258881, video 258884, BOI 255999, EOI 258882; stop tokens 1, 106
(<end_of_turn>).
Performance (M-series Mac, GPU)
- Decode: ~39–46 tok/s · Prefill: ~290–313 tok/s · Warm load: ~2 s
- Text quality verified greedy + sampled; multimodal pipeline verified token-exact against the HF reference implementation (bf16 eager).
Usage
Drive with the CoreAILanguageModels Swift package from
apple/coreai-models (text path works
out of the box via main), or CoreAI.framework directly. The multimodal
path requires client-side preprocessing that mirrors the HF
Gemma4UnifiedProcessor: aspect-preserving resize (divisible by 48), 16 px
patchify, 3×3 patch merge to 6912-dim patches with XY position ids, audio
framing into 640-sample tokens, placeholder-token expansion, and the boolean
masks described above.
Provenance & license
- Source weights: google/gemma-4-12B-it, Apache 2.0.
- Modifications: conversion to Core AI
.aimodelviatorch.export+coreai-torch; INT4 block-32 weight-only quantization of the decoder (embedders kept bf16); multi-function graph packaging described above. - This distribution remains under Apache 2.0. See
LICENSEandNOTICE.
- Task
- Image-Text-to-Text
- License
- apache-2.0
- Created
- Jun 11, 2026
- Updated
- Jun 12, 2026