What changed in v1.3
- Weights: a new full fine-tune of
Qwen/Qwen3.5-4B on an expanded training mix of public datasets (official
training splits) and synthetic decision data covering choice, yes/no and score questions. The
architecture, tokenizer, prompt format (jev_render_v3) and attention mode are the same as in v1.2.
- Speed: the bundled server now uses CUDA graphs; median latency per request is about half that of v1.2
(67.9 ms to 31.9 ms on one A40), with the same probabilities as the eager path.
- Memory: about 1.2 GiB less GPU memory after loading.
- Serving settings: updated in
decision_config.json.
v1.3.1 (serving package only): the weights and decision_config.json are those of v1.3.0, and the probabilities
are identical (bit for bit) to v1.3.0's. The serving package torchcast_decision/ was rewritten by Torchcast AI; the
server now answers every error with JSON and a status code (503 when the GPU runs out of memory, 500 for anything
else) instead of closing the connection. The Apple Silicon (MLX) and GGUF backends, which could not run this model,
were removed.
Results
On the JevBench leaderboard (release v1.7.9, as of 2026-10-27), Torchcast Decision 4B v1.3 is
#1 among open-weight models by composite score:
Table with columns: Model, Composite, Capability, Intelligence, Calibration, Speed, Cost| Model | Composite | Capability | Intelligence | Calibration | Speed | Cost |
|---|
| Torchcast Decision 4B v1.3 | 76.16 | 77.50 | 67.15 | 87.85 | 92.45 | 64.81 |
| H2O-Lightning-4B v1.1 | 73.78 | 75.00 | 60.04 | 89.95 | 92.37 | 64.05 |
| Torchcast Decision 4B v1.2 | 73.00 | 72.61 | 60.26 | 84.95 | 90.89 | 64.81 |
Source: benchmarkheaven.com/jev-models. Measured by the JevBench maintainers
at revision 004acea2 (tag v1.3.0; v1.3.1 has the same weights and probabilities) with the bundled server and settings, on the second regular v1.6 draw (anchor
runs pending, so scores may be re-placed when the board's anchor offsets are applied).
Artifact
- Pinned revision: tag
v1.3.1 of this repository (the board measured tag v1.3.0, same weights).
- Weight SHA-256: see
SHA256SUMS.
- Served model name:
torchcast-decision-4b-v1.3.
Serving settings
Serve the model through the bundled torchcast_decision package; decision_config.json holds the serving settings.
Within a prompt, the full-attention layers use no causal mask (as in training), so loading the weights with plain
transformers, vLLM, llama.cpp or MLX gives different probabilities. Prompts longer than 16,384 tokens keep the head and the tail of the state. Repeated runs on the same GPU type
give identical probabilities. See NOTICE and the serving instructions.
Intended use and limitations
English text-based decision research, such as classification, routing and bounded rubric evaluation. The server
returns decisions and does not execute actions. Probabilities can be unreliable on new domains.
Licence and attribution
Model weights: Apache License 2.0 (see LICENSE). Base model: Qwen3.5-4B by the Qwen team, Apache
License 2.0, Copyright 2026 Alibaba Cloud (LICENSE-qwen-Apache-2.0, NOTICE). Serving package: Apache License 2.0,
written by Torchcast AI (torchcast_decision/LICENSE, torchcast_decision/NOTICE). This
project is independent of TypeSafe AI and the JevBench maintainers. Earlier releases keep their own licence: v1.1 (tag v1.1.0) remains under CC BY-NC 4.0.