inferoid-notes-e2b

The notes model behind Inferoid Notes: meeting notes written on your Mac, from a transcript of the call. Nothing leaves the Mac.

  • Base: Gemma 4 E2B, fine-tuned for meeting notes, MLX 4-bit (2.5 GB).
  • For Macs with 8 GB of memory or more.
  • Output: JSON with title, summary, key points, decisions, action items (owner, due date) and open questions.

Results

On 23 held-out synthetic business calls (written transcripts with speech-recognition-style errors, roughly 35-70 minutes of speech each), judged by independent models:

model coverage mistakes per call usefulness (1-10) median time per call (24 GB M4)
inferoid-notes-e2b (22 calls) 94.8% 6.1 7.0 17 s
inferoid-notes-e4b 96.7% 3.0 7.9 40 s
Claude Opus 5.5 (cloud) 98.9% 3.2 8.8 cloud

Judge: GPT-6.1 Sol. The lighter model for 8 GB Macs is twice as fast but makes about twice the mistakes of the E4B; use the E4B if your Mac has 16 GB or more.

Mistakes = statements in the notes that the call does not support (wrong owner, invented question, hedge stated as fact). These are synthetic calls, not recordings of real meetings.

Use

The easiest way is the app: uv tool install git+https://github.com/inferoid/inferoid then inferoid add notes.

Directly, with mlx-lm:

pip install mlx-lm
mlx_lm.server --model Inferoid/inferoid-notes-e2b --port 8090

Send the raw Gemma 4 prompt without the thinking token (<bos><|turn>system\n...<turn|>\n<|turn>user\n...<turn|>\n<|turn>model\n); the system prompt the app uses is in Engine.swift.

Downloads last month
84
Safetensors
Model size
5B params
Tensor type
U32
Β·
BF16
Β·
MLX
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for Inferoid/inferoid-notes-e2b

Quantized
(477)
this model