Zircon-0.6B-v2-mlx
Zircon-0.6B-v2-mlx by FahrenheitResearch is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text.
Pricing
No hosted price is listed. The weights are open: the cost is your own compute.
Specifications
- Provider
- FahrenheitResearch
- Parameters
- 596M
- Released
- Sep 2026
- Open weights
- Yes
- Question types
- Choice (one of N options), Score (ordered rubric), Yes / no
- Mechanism
- Decoder LM with a decision readout
- Backbone
- Qwen/Qwen3-0.6B
- Jev-compatible request
- Yes
- Runs on CPU
- Yes
- License
- apache-2.0
- Hugging Face
- FahrenheitResearch/Zircon-0.6B-v2-mlx
Compare Zircon-0.6B-v2-mlx with…
FAQ
How much does Zircon-0.6B-v2-mlx cost?
Zircon-0.6B-v2-mlx has no hosted price listed; its weights are open, so the cost is the compute you run it on.
What questions can Zircon-0.6B-v2-mlx answer?
Zircon-0.6B-v2-mlx answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.
Is Zircon-0.6B-v2-mlx well calibrated?
No calibration measurement for Zircon-0.6B-v2-mlx is recorded yet.
Is Zircon-0.6B-v2-mlx open weight, and can it run on a CPU?
Yes, Zircon-0.6B-v2-mlx has open weights. It is small enough to run on a CPU.
Data as of 2026-10-14. Source: Metatext decision-model catalogue, 2026-10-14 (Hugging Face). Pricing is per 1M tokens (USD); confirm with the provider before production use.