Introducing TFM-1.6

The results of a first attempt at creating a capable small model.

March 24th, 2026

Today, we're releasing TFM-1.6, the latest model from Astar Labs.

TFM-1.6 is a real step up from TFM-1.5, our first experimental model. Pretrained on the full SlimPajama-6B dataset, and fine-tuned on OpenOrca, it brings noticeably better knowledge and instruction following, whilst staying small and efficient.

Model Details

  • Parameter Count: 167M
  • Vocabulary: 24k
  • Context Window: 4096

TFM-1.6 has been trained in full in 10 days on a single NVIDIA RTX 5090.

Two versions of the model are available:

  • TFM-1.6 (Chat) - conversational, able to follow tasks
  • TFM-1.6 (Base) - autocomplete model

Benchmark Results

TFM-1.6 Benchmark Results
Model/Benchmark TFM-1.6 Llama 2 70B Grok-0 (33B) GPT-3.5 Grok-1 Mistral Large Claude 2 Grok-1.5
GSM8k 1.60%
8-shot
56.80%
8-shot
57.10%
8-shot
57.10%
8-shot
62.90%
8-shot
81.00%
8-shot
88.00%
8-shot
90.00%
8-shot
MMLU 26.40%
5-shot
68.90%
5-shot
65.70%
5-shot
70.00%
5-shot
73.00%
5-shot
81.20%
5-shot
75.00%
5-shot + CoT
81.30%
5-shot
HumanEval 0.00%
0-shot
29.90%
0-shot
39.70%
0-shot
48.10%
0-shot
63.20%
0-shot
45.10%
0-shot
70.00%
0-shot
74.10%
0-shot

TFM-1.6 has been benchmarked against 3 standard benchmarks: GSM8k, MMLU, and HumanEval.

TFM-1.6 is still a small model, with a lot of room for improvement, but it's the strongest one I've built so far, and a solid foundation for what comes next. You can chat with TFM-1.6, as well as the older TFM-1.5 model, right here on the Astar Labs website.


TFM is free to use. It is not affiliated with any company, research institution, or commercial entity. It's just a project. A very personal one.