TokForge Chat Models (MNN)
Collection
Start here: official open models as MNN bundles for chatting on your phone with TokForge, smallest first. โข 20 items โข Updated โข 1
Hugging Face's SmolLM2 1.7B Instruct as a 4-bit MNN bundle for chatting on your phone with TokForge.
Published by TokForge for on-device inference.
| What it is | Chat model |
| Format | MNN bundle, 4-bit weights (block 128) |
| Runs on | Android phones (CPU, OpenCL or Vulkan GPU) |
| Phone class | No catalog class; needs more free RAM than its 1.16 GB of weights |
| Download | 1.17 GB (8 files) |
| Base model | HuggingFaceTB/SmolLM2-1.7B-Instruct |
| License | Apache-2.0 |
Runs on-device in the TokForge app.
SmolLM2-1.7B-Instruct-MNN and download it.Collections: TokForge Chat Models (MNN).
| File | Size | What it is |
|---|---|---|
config.json |
210 B | MNN runtime settings |
embeddings_bf16.bin |
201 MB | Token embeddings (bf16) |
export_args.json |
1.11 KB | Export settings used for the conversion |
llm.mnn |
419 KB | Model graph |
llm.mnn.json |
843 KB | Model graph as JSON (reference copy) |
llm.mnn.weight |
963 MB | Model weights |
llm_config.json |
621 B | Model settings and chat template |
tokenizer.txt |
885 KB | Tokenizer |
Hugging Face's own SmolLM2 1.7B Instruct is a compact model designed for on-device use. It was trained on 11 trillion tokens and then instruction-tuned. It suits quick questions and answers, text completion and simple tasks rather than long, deep answers.
| Architecture | LlamaForCausalLM (24 layers, 2048 hidden) |
| Parameters | 1.7B (4-bit quantized) |
| Quantization | W4A16 (4-bit weights, block size 128) |
| Vocab | 49,152 tokens |
| Setting | Value |
|---|---|
| Backend | OpenCL (Qualcomm) / Vulkan (MediaTek) / CPU (fallback) |
| Precision | Low |
| Threads | 4 |
| Thinking | Off |
Converted using MNN's llmexport pipeline:
python llmexport.py --path HuggingFaceTB/SmolLM2-1.7B-Instruct --export mnn --quant_bit 4 --quant_block 128
SmolLM2 1.7B Instruct is released by Hugging Face under the Apache-2.0 license.
Base model
HuggingFaceTB/SmolLM2-1.7B