You can deploy this model and start earning money today!

Intension/
anemll-qwen3-1.7b-ctx2048

Name: anemll-qwen3-1.7b-ctx2048
Availability: InStock

Views

No views yet

anemll-qwen3-1.7b-ctx2048

Qwen3-1.7B converted to Core ML for the Apple Neural Engine using ANEMLL v0.3.5. This is a redistribution of ANEMLL's published conversion (anemll-Qwen-Qwen3-1.7B-ctx2048), hosted here so the download source is under our control.

This artifact powers on-device session classification in Intension on lower-memory Macs (8GB tier). It is downloaded automatically by the app; there is nothing to install manually.

Conversion parameters

Parameter	Value
Base model	Qwen/Qwen3-1.7B
Context length	2048
Batch size (prefill)	64
FFN / LM-head quantization	LUT6, per-channel 4
Chunks	2
ANEMLL version	0.3.5

See meta.yaml for the full conversion record.

Layout

qwen_embeddings.mlmodelc — embeddings
qwen_FFN_PF_lut6_chunk_0Xof02.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: ANEMLL, MIT — original converted artifact published by the ANEMLL project.
This repository redistributes a derivative (quantized, Core ML-compiled) form of the base model under Apache-2.0.

Intension/anemll-qwen3-1.7b-ctx2048

anemll-qwen3-1.7b-ctx2048

Conversion parameters

Layout

Licenses & attribution

Intension/
anemll-qwen3-1.7b-ctx2048