Firworks/Magistral-Small-2509-Text-Only-nvfp4

🤗 Hugging Face sourceapache-2.013.8B params15 GBsafetensors✓ 5 checksumsupdated today

Submit in one command

Run it next to your model folder. It makes the torrent, checks your files against Hugging Face, and submits it. You just start seeding and paste your key from your account. It only reads your files and never changes them. Read the script first if you like.

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo Firworks/Magistral-Small-2509-Text-Only-nvfp4 ./model-folder

Needs a seeder →

Magistral-Small-2509-Text-Only-nvfp4

Format: NVFP4 — weights & activations quantized to FP4 with dual scaling.
Base model: Darkhn/Magistral-Small-2509-Text-Only
How it was made: One-shot calibration with LLM Compressor (NVFP4 recipe), long-seq calibration with HuggingFaceH4/ultrachat_200k.

Notes: Keep lm_head in high precision; calibrate on long, domain-relevant sequences.

Check the original model card for information about this model. This is a version of Magistral Small 2509 with the vision capabilities removed.

If there are other models you're interested in seeing quantized to NVFP4 for use on the DGX Spark, or other modern Blackwell (or newer) cards let me know. I'm trying to make more NVFP4 models available to allow more people to try them out.