qwen2.5-coder-1.5b

A Core AI bundle of Qwen/Qwen2.5-Coder-1.5B-Instruct for the Aether SDK (iOS and macOS 27+).

• Source: Qwen/Qwen2.5-Coder-1.5B-Instruct at revision 2e1fd397ee46e1388853d2af2c993145b0f1098a, licence Apache-2.0. The licence is included as LICENSE.
• Changes from the source: converted from PyTorch to Core AI (.aimodel) by Aether forge (recipe qwen2.5-coder-1.5b@1). Weights are int8-linear-perchannel (8-bit weights). The tokenizer files are the source's own.

Variants

Variant	Platform	Arch	Compute	Compiled	Download
macos-any-gpu	macos	any	gpu	no (specialized on first load)	1.56 GB
ios-any-gpu	ios	any	gpu	no (specialized on first load)	1.56 GB
ios-h18p-gpu	ios	h18p	gpu	yes	1.56 GB

Verification

Every row is a record in verification/ about exactly these bytes (matched by bundle digest). Reference rows are strict T2 passes of the unquantized export on the same fixture, in verification/reference/.

Variant	Tier	Result	Detail	Device	OS build	Compute	Record
ios-any-gpu	T0	pass		iPhone18,2	24A437	target	e3683f66
ios-any-gpu	T2	pass	18/18 strict; profile quantized-8bit; fixture c9295a19d68af168	iPhone18,2	24A437	target	5a760704
ios-h18p-gpu	T0	pass		iPhone18,2	24A437	target	2cf54018
ios-h18p-gpu	T2	pass	18/18 strict; profile quantized-8bit; fixture c9295a19d68af168	iPhone18,2	24A437	target	b294f478
macos-any-gpu	T0	pass		Mac17,6	26A428	target	209f9311
macos-any-gpu	T1	pass		Mac17,6	26A428	target	1b33381e
macos-any-gpu	T2	pass	18/18 strict; 18/18 strict; profile quantized-8bit; fixture c9295a19d68af168	Mac17,6	26A428	target	2f0a4d34
unquantized reference (not published)	T2	pass	18/18 strict; 18/18 strict; profile strict; fixture c9295a19d68af168	Mac17,6	26A428	target	33e0418f

The quantized profile also requires: T2 strict on the unquantized reference export (met by the reference row).

Use

aether run qwen2.5-coder-1.5b --prompt "Hello"

import Aether

let aether = try Aether()
let chat = try await aether.chat("qwen2.5-coder-1.5b")
let reply = try await chat.respond(to: "Hello")
print(reply.text)