olmo-2-1b-instruct

A Core AI bundle of allenai/OLMo-2-0425-1B-Instruct for the Aether SDK (iOS and macOS 27+).

• Source: allenai/OLMo-2-0425-1B-Instruct at revision 48d788eca847d4d7548f375ad03d3c9312f6139e, licence Apache-2.0. The licence is included as LICENSE. allenai/OLMo-2-0425-1B-Instruct declares apache-2.0 in its model card but ships no licence file; LICENSE is the canonical text from apache.org.
• Changes from the source: converted from PyTorch to Core AI (.aimodel) by Aether forge (recipe olmo-2-1b-instruct@1). Weights are int8-linear-perchannel (8-bit weights). The tokenizer files are the source's own.

Variants

Variant	Platform	Arch	Compute	Compiled	Assets	Download
macos-any-gpu	macos	any	gpu	no (specialized on first load)	olmo_2_1b_instruct.aimodel 1.69 GB	1.7 GB
ios-any-gpu	ios	any	gpu	no (specialized on first load)	olmo_2_1b_instruct.aimodel 1.69 GB	1.7 GB
ios-h18p-gpu	ios	h18p	gpu	yes	olmo_2_1b_instruct.h18p.aimodelc 1.69 GB	1.7 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	24A446	target	eb2601c9
ios-any-gpu	T2	pass	19/19 strict; profile quantized-8bit; fixture 7b97ff11db95049d	iPhone18,2	24A446	target	6022bca4
ios-h18p-gpu	T0	pass		iPhone18,2	24A446	target	f9346e21
ios-h18p-gpu	T2	pass	19/19 strict; profile quantized-8bit; fixture 7b97ff11db95049d	iPhone18,2	24A446	target	d80ed5ef
macos-any-gpu	T0	pass		Mac17,6	26A434	target	cb07238b
macos-any-gpu	T1	pass		Mac17,6	26A434	target	c9a063cd
macos-any-gpu	T2	pass	19/19 strict; 19/19 strict; profile quantized-8bit; fixture 7b97ff11db95049d	Mac17,6	26A434	target	8e88f60c
unquantized reference (not published)	T2	pass	19/19 strict; 19/19 strict; profile strict; fixture 7b97ff11db95049d	Mac17,6	26A434	target	87dd4aec

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

Use

aether run olmo-2-1b-instruct --prompt "Hello"

import Aether

let aether = try Aether()
let chat = try await aether.chat("olmo-2-1b-instruct")
let reply = try await chat.respond(to: "Hello")
print(reply.text)