Cactus Hybrid

A small, on-device model is fast and private, but sometimes wrong.

At Cactus we post-train models to know when they are wrong: we ship probes

inside the checkpoint that score every answer with a confidence between

0 and 1, returned as structured data (never parsed out of the answer text).

Answer on-device when confidence is high; you can re-route to a bigger

model when it's low:

We start the rollout with Gemma 4 E2B Hybrid, all builds live in the

Cactus Hybrid collection

on Hugging Face.

Cactus Hybrid collection

Gemma 4 E2B hybrid, the smallest Gemma model, matches Gemini 3.1 Flash-Lite

on most benchmarks by routing only 15–35% of queries to the Gemini 3.1 Flash-Lite and

running the remnant itself.

N/B: Quantisation quality is measured on Cactus Quants

which performs well at uniform quantization.

Cactus Quants

Developers are encouraged to benchmark for Unsloth, GGUF, and MLX quantization independently.

Cactus

MLX

Transformers

Load the model with an explicit .to(device), not device_map="auto": the

probe scores generations outside the module forward() path, so weights that

accelerate offloads (left on the meta device) crash the confidence read.

llama.cpp

llama.cpp is C++, so the probe is a patch you compile into the engine (see

patches/llama.cpp/). Build the patched server once:

patches/llama.cpp/

Then serve and query it like any llama-server — the response carries a

top-level confidence field:

Routing Quality (AUROC)

Gemma 4 E2B Hybrid AUROC measures how well the the separates wrong answers from right ones

(higher = better, 0.5 is random, 1.0 is perfect):

The strongest result: the probe was trained on zero audio data, yet achieves

0.79–0.88 AUROC on four audio benchmarks (two transcription, one audio MCQ, one

out-of-domain transcription).

This rules out surface-level explanations, the probe

is reading a modality-independent correctness signal from the hidden state, not

memorizing patterns from training data.

MIT-licensed. Gemma model use is subject to the Gemma terms.