anemll-qwen3-4b-2507-ctx2048

Intension/anemll-qwen3-4b-2507-ctx2048

anemll-qwen3-4b-2507-ctx2048 is a machine learning model from Intension. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for coreml. The card lists the license as apache-2.0.

Qwen3-4B-Instruct-2507 converted to Core ML for the Apple Neural Engine using ANEMLL v0.3.5.

Downloads · 30 days

9% of all-time downloads

All-time downloads

277

Public

Repo size

3.9 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin3.8 GB · 100%

At a glance

Library: coreml
License: apache-2.0
Model type: qwen3
Access: Public
Created: Jul 8, 2026
Updated: Jul 8, 2026
SHA: 092d6e95

Base models

Qwen/Qwen3-4B-Instruct-2507

Model card

From the Hugging Face model README

anemll-qwen3-4b-2507-ctx2048

Qwen3-4B-Instruct-2507 converted to Core ML for the Apple Neural Engine using ANEMLL v0.3.5.

This artifact powers on-device session classification in Intension. It is downloaded automatically by the app; there is nothing to install manually.

Conversion parameters

Parameter	Value
Base model	Qwen/Qwen3-4B-Instruct-2507
Context length	2048
Batch size (prefill)	64
FFN / LM-head quantization	LUT6, per-channel 4
Chunks	4
ANEMLL version	0.3.5

See meta.yaml for the full conversion record.

Layout

qwen_embeddings.mlmodelc — embeddings
qwen_FFN_PF_lut6_chunk_0Xof04.mlmodelc — FFN + prefill chunks
qwen_lm_head_lut6.mlmodelc — LM head
meta.yaml — model/conversion metadata consumed by the runtime
Tokenizer files (tokenizer.json, tokenizer_config.json, vocab.json, merges.txt)

Licenses & attribution

Conversion pipeline: ANEMLL, MIT.
This repository redistributes a derivative (quantized, Core ML-compiled) form of the base model under Apache-2.0.

Library: coreml
Type: qwen3
License: apache-2.0
Created: Jul 8, 2026
Updated: Jul 8, 2026