bobbydeveloper2014/mamba-siso-175m-nimq

Mamba-3 SISO 187M (requested repo slug: 175M)

Quantized Mamba-3 SISO checkpoint in Nimformers NIMQ format, paired with its LoRA/Linear++ fine-tune. The base weights use FP4-KM; the LoRA checkpoint is NIMBIN4. The repo slug follows the requested name. Upstream model: state-spaces/mamba3-siso-187m.

Contents

• mamba3_siso_187m.nimq — FP4-KM base
• lora.bin — 11 R + G LoRA/Linear++ checkpoint
• config.json, tokenizer.json, tokenizer_config.json, special_tokens_map.json — alongside the base model

Architecture: 12 layers, hidden 768, 24 heads, state 128. The LoRA uses Mamba-3 blocks with a gated Linear++ branch (G) at the final layer. R marks pretrained Mamba-3 blocks.

Download for this repository's inference CLI

From the Nimformers Framework root, download into the expected local layout:

hf download bobbydeveloper2014/mamba-siso-175m-nimq \
  --local-dir test/mamba3/models

Then run make -f test/mamba3/Makefile infer and use the checkpoint path test/mamba3/models/lora.bin. The tokenizer sidecar and model config are included for that local layout.

The original upstream Mamba-3 model card is state-spaces/mamba3-siso-187m.

Tokenizer and config files are stored at the repo root beside the model file. The local tokenizer sidecar points to test/mamba3/models.

Framework

Use this model with Nimformers Framework.