Qwen3.5-9B-MNN (mirror with MTP head)
Published by TokForge for on-device inference.
TokForge
- Website: https://tokforge.ai
- Discord: https://discord.gg/Acv3CBtfVm
- Google Play: https://play.google.com/store/apps/details?id=dev.tokforge
- iOS TestFlight: https://testflight.apple.com/join/jnufjzRr
Runs on-device in the TokForge app.
This repo mirrors taobao-mnn/Qwen3.5-9B-MNN at commit 149e1e052267ffa377b87e3bb0ddb75f46217a9a byte for byte
(every file below has the same sha256 as the original; the MNN conversion and all credit for it belong to the
taobao-mnn team, the model to the Qwen team) and adds an optional multi-token-prediction (MTP) head next to the
unchanged trunk, used by TokForge on the MNN CPU route.
Trunk files (identical to taobao-mnn/Qwen3.5-9B-MNN @ 149e1e0522)
| file | bytes | sha256 |
|---|---|---|
config.json |
652 | 92853033efe602f95efca3e1c05cd8b108f973c8beed417843a9671f8147ed8d |
embeddings_bf16.bin |
2,034,237,440 | d87d444a38822588c6c1ed07dec4404ccd8d526f57d58565cbbbf60acc758afe |
export_args.json |
1,041 | 5d9cb1fc15d189e86b3117576f0e7a6875295a16628f6dc9d9ad4fda9ef73d19 |
llm.mnn |
3,651,096 | fe9101e1b1754c304bef2091114c260cffbbac0ca6180110af0a04efd7f24c13 |
llm.mnn.json |
9,172,377 | 7d87ce4a07e74366d4a2126369ac8f8ac753612bb3b1a9cb16e062e438d816ee |
llm.mnn.weight |
4,961,957,226 | 896bf5a7b7e164186f1c0d065cb6d92306c9aa9c3cb62047531e24fa08c033af |
llm_config.json |
8,582 | 6c7547f03faf34af1a916e4cd700bf3c5be7e14ef75da75a04f88bc1ea49e86b |
tokenizer.txt |
6,465,727 | 7e75de1f279a10b65bd9dc1a5207205cb8993823861c4c42bbbd74e48e1c23a4 |
visual.mnn |
547,632 | f85e3ea5a2b51f267d8d8a857cc05da4ea2ae1f5fc1f98ec676d8130f31df748 |
visual.mnn.weight |
258,831,244 | 3c9988e012c35b1d22e03412f316b2dc24e993ac8b149b3ad2b4095917f3c90c |
MTP head (optional add-on)
Exported from Qwen/Qwen3.5-9B @ c202236235762e1c871ad0ccb60c8ee5ba337b9a with MNN-TokForge llmexport --mtp --mtp_only --quant_bit 4 --quant_block 64
and a 32k draft vocabulary (mtp-v32k.mnn.vocab, int32 token ids). Load with speculative_type: "mtp",
mtp_model: "mtp-v32k.mnn", draft_predict_length: 1. The trunk verifies every drafted token, so output quality is
the trunk's own. Host acceptance only so far (depth 1: code 85%, advice 55%, chat 61%, RAG 94% of drafts accepted); TokForge checks it per phone before it runs.
| file | bytes | sha256 |
|---|---|---|
mtp-v32k.mnn.vocab |
132,160 | 80af0c499240994c092bb3e79fe4d32a4e9e8dbc82fbbf8d728158f11fbae1b3 |
mtp-v32k.mnn.weight |
236,794,054 | 20606e4785e6c724b1f9038e2835c65ba6608ce995988a855b2590afc2b5c700 |
mtp-v32k.mnn |
34,024 | 66b26ccdc76d324423dd5ff5ba50c78276c98ade011b772f69231a4c395ce5f3 |
License: Apache-2.0, as the original model and conversion.
Credits
- Qwen3.5-9B by the Qwen team (Alibaba Cloud) (Hugging Face). Used under the Apache-2.0 license.
- The MNN conversion (every trunk file here is byte-identical to it) by the taobao-mnn team (Hugging Face). Used under the Apache-2.0 license.
- The MTP head is exported from Qwen/Qwen3.5-9B (Apache-2.0) by TokForge with llmexport from TokForge's fork of MNN.