# Mikhail Gribov: typecastlm

> Typed decisions from a frozen, cut-down Qwen3.5-4B: the last four blocks are removed and a computed 39-row head reads yes/no, true/false/unsure, one of 2 to 26 options or a level on a scale in one forward pass, with a temperature per mode. Training-free; Apache-2.0.

- Page: https://systemonemodels.ai/mikhail-gribov/typecastlm
- API: https://api.systemonemodels.ai/v1/models/mikhail-gribov/typecastlm
- Download: `pip install systemonemodels && systemone pull mikhail-gribov/typecastlm`

## Facts

| | |
|---|---|
| Maker | Mikhail Gribov (https://systemonemodels.ai/mikhail-gribov) |
| Decides | choice, score, noul |
| Architecture | typecastlm |
| Base model | qwen/qwen3.5-4b |
| Parameters | 3.8B |
| Context | 32K tokens |
| Licence | apache-2.0 |
| Availability | Open weights |
| Released | 2026-09-24 |
| Latest version | 2026.09 |

## Reported evaluation

Suite: SuperGLUE BoolQ validation (3,000 rows), accuracy at 0.5; the maker's own run. Numbers are the publisher's own.

- Decision accuracy: 85.6%
- Calibration error (ECE): 0.052
- Median latency: 48 ms

## Model card

<!-- generated by scripts/seed_catalog.py; edit content/models/catalog.yaml -->

# typecastlm-qwen3.5-3.8b

Typed decisions from a frozen, cut-down Qwen3.5-4B: the last four blocks are removed and a computed 39-row head reads yes/no, true/false/unsure, one of 2 to 26 options or a level on a scale in one forward pass, with a temperature per mode. Training-free; Apache-2.0.

Per the NOTICE, Qwen3.5-4B blocks 0 to 27 are kept bit for bit and blocks 28 to 31 removed, so it cannot generate text; the head's vectors are computed from the model's own output rows, not trained. Four modes: noul, tfu (adds "unsure"), choice (2 to 26 options, degrading past six) and scale. The answer follows an option's position more than its name, by the maker's own measurement. One temperature per mode, fitted on unnamed broad sets; the maker advises refitting on about 200 labelled rows. Runs as a transformers checkpoint or as llama.cpp GGUFs through the maker's reader; the typecastlm server offers a Jev-compatible HTTP API. Not affiliated with TypeSafe AI.

## What it decides

- **choice** — picks one option from a set
- **score** — places the input on an ordered scale
- **noul** — answers a yes/no question with one probability

## At a glance

| | |
|---|---|
| Parameters | 3.76B |
| Base model | `Qwen/Qwen3.5-4B` |
| Maker | Mikhail Gribov |
| Released | 2026-09-24 |
| License | apache-2.0 |
| Reported accuracy | 85.6% |
| Reported latency | 48 ms p50 / 75 ms p90 for inputs under 200 tokens on a 16 GB consumer GPU |

## Get the weights

```bash
pip install systemonemodels
systemone pull mikhail-gribov/typecastlm
```

The files are served from the maker's Hugging Face repository, [`mihailgribov/typecastlm-qwen3.5-3.8b`](https://huggingface.co/mihailgribov/typecastlm-qwen3.5-3.8b), and verified against the checksums recorded here.

## Read more

- [Model card](https://huggingface.co/mihailgribov/typecastlm-qwen3.5-3.8b)
- [Code](https://github.com/mihail-gribov/typecastlm)

---

*This page was opened by System One for Mikhail Gribov, who can claim the organisation and take it over at any time.*

---

From System One Models — https://systemonemodels.ai/ · every System One model: https://systemonemodels.ai/system-one-models