Granite 4.0 H 350M

A Core AI bundle of ibm-granite/granite-4.0-h-350m for the Aether SDK (iOS and macOS 27+).

  • Source: ibm-granite/granite-4.0-h-350m at revision 3b17b717b8f2f5d305b0a92c1491e239aeda19c8, licence Apache-2.0. The licence is included as LICENSE. ibm-granite/granite-4.0-h-350m 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 granite-4.0-h-350m@5). Weights are float16 (16-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) granite_4_0_h_350m.aimodel 681.7 MB 691.4 MB
ios-any-gpu ios any gpu no (specialized on first load) granite_4_0_h_350m.aimodel 681.7 MB 691.4 MB

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 bb5cc35b
ios-any-gpu T2 pass 19/19 strict; profile strict; fixture 46a9e3c33d3c436b iPhone18,2 24A446 target b776479b
ios-any-gpu T3 pass copy-fidelity-v1; 78.0% vs reference 78.0%; 50 items iPhone18,2 24A446 gpu 5b71226d
macos-any-gpu T0 pass Mac17,6 26A434 target 2426b3d8
macos-any-gpu T1 pass Mac17,6 26A434 target 02e7baec
macos-any-gpu T2 pass 19/19 strict; 19/19 strict; profile strict; fixture 46a9e3c33d3c436b Mac17,6 26A434 target edc5dc4b
macos-any-gpu T3 pass gsm8k-test-500; 5.2% vs reference 5.4%; 500 items Mac17,6 26A434 gpu 685a6841
macos-any-gpu T3 pass copy-fidelity-v1; 78.0% vs reference 78.0%; 50 items Mac17,6 26A434 gpu b446ff57
unquantized reference (not published) T2 pass 19/19 strict; 19/19 strict; profile strict; fixture 46a9e3c33d3c436b Mac17,6 26A434 target 048160d8

Use

aether run granite-4.0-h-350m --prompt "Hello"
import Aether

let aether = try Aether()
let chat = try await aether.chat("granite-4.0-h-350m")
let reply = try await chat.respond(to: "Hello")
print(reply.text)
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for aether-models/granite-4.0-h-350m

Finetuned
(15)
this model