Tin 0.8B

Tin 0.8B

A small model that knows Tin, the typed programming language where agents and tools are part of the syntax. It writes Tin programs, fixes them from the compiler's errors, and runs a check-and-fix loop with tin_check / tin_run tools. Made by Γ‡ağatay Γ‡alΔ± (@cagataycali).

This is the bf16 build for transformers and further tuning. For phones and Macs use cagataydev/tin-0.8b-4bit. Post-tuned from cagataydev/loopl-0.8b (Qwen3.5-0.8B).

Scores

Scorecard

probe Tin 0.8B Qwen3.5 0.8B
Says it is Tin 93.8 60.4
Tin knowledge 50.1 15.1
Writes Tin 37.5 0
Fixes Tin 88.8 30.8
Fixes stacked bugs 89 7.3
Agent loop Β· native 32.5 0

% pass on a held-out set, graded by the real Tin compiler. "Writes Tin" means the program compiles and prints exactly the expected output on the first try.

Run it

curl -fsSL https://tin.ad/install.sh | bash
tin model pull tin:0.8b   # then any agent without a model: line uses it

Or directly with mlx-lm:

pip install -U mlx-lm
mlx_lm.generate --model cagataydev/tin-0.8b-4bit --prompt "Write a Tin program with a guarded tool fn deleteFile."

All sizes

size writes Tin fixes Tin agent loop phone build
0.8B 37.5 88.8 32.5 tin-0.8b-4bit
2B 54.1 92.5 55 tin-2b-v3-4bit
4B 68.3 97.2 65 tin-4b-4bit

Limits

  • About 62% of first tries fail tin check or print the wrong thing, so always run the compiler.
  • It knows Tin as of the training commit; newer std functions may be missing.
  • Small model: details like flag names and error codes are often wrong.

Licence

Apache-2.0, like the base Qwen3.5 model.

Downloads last month
21
Safetensors
Model size
0.9B params
Tensor type
BF16
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for cagataydev/tin-0.8b

Finetuned
(1)
this model
Quantizations
3 models

Collection including cagataydev/tin-0.8b