- Services
Valen-Decision-1.5-2B is a 2.22B parameter decision model from the Valen Team, built as a full fine-tune of Qwen3.5-2B. It answers predicate, choice, score and bounding box questions in a single forward pass, for jobs such as classifying customer messages, screening product images and tagging actions in video. Weights are open under Apache-2.0, and a free hosted API serves the 0.8B, 2B and 4B sizes with no API key. It scores 61.89 on the Jev Decision Index 0.4.1.
A solid 2.22B-parameter dense decision model from Valen. Treat the modality benchmarks above as the leading indicator of fit — composite scoring across modalities is still maturing.
Generated from this model’s benchmarks and ranking signals. Editor reviews refine it over time.
Access model weights, configuration files, and documentation.
Benchmark data sourced from: Hugging Face, Arena.ai, Artificial Analysis.
The top devices for this model at 4-bit, ranked by fit and speed.
| Device | Grade | VRAM |
|---|---|---|
| ACEMAGIC M1A Pro (i9-13900HK + ARC A770)ACEMAGIC | SS | 1.9 GB |
| Acer Veriton GN100 AI MiniAcer | SS | 1.9 GB |
| AI TOP ATOM ATAGB10-9003Gigabyte | SS | 1.9 GB |
| AMD Instinct MI300XAMD | SS | 1.9 GB |
| AMD Instinct MI325XAMD | SS | 1.9 GB |
Cheapest current cloud rentals with at least 2 GB VRAM, refreshed hourly.
Advertising disclosure: we earn commissions when you shop through the links below.
| Option | Cost / GPU-hour |
|---|---|
NVIDIA GeForce RTX 3060Vast.ai · Spot · 12 GB VRAM | $0.06 |
NVIDIA GeForce RTX 3060Vast.ai · On-Demand · 12 GB VRAM | $0.06 |
NVIDIA GeForce RTX 5060 TiVast.ai · Spot · 16 GB VRAM | $0.06 |
NVIDIA GeForce RTX 3080 TiVast.ai · Spot · 12 GB VRAM | $0.07 |
NVIDIA Tesla V100 16GBVast.ai · Spot · 16 GB VRAM | $0.07 |
Per-GPU rate across RunPod, the Vast.ai marketplace, DigitalOcean, and Vultr.
Spot tier is interruptible. Plan for restarts when comparing against on-demand prices.
Valen-Decision-1.5 adds block-bidirectional attention and a bbox grounding head to the Qwen backbone, so one forward pass returns probabilities for predicate, choice and score questions plus a box for each bbox question. The 1.5 generation ships in five sizes (0.8B, 2B, 4B, 9B, 27B), each in native Transformers weights, ONNX and GGUF formats; the native weights keep the backbone in BF16 and the decision and grounding heads in FP32. Training code is released for fine-tuning on private data, and the model supports both the SystemOne and Decisions API formats. Training data is not public.
Explore the Provider
Aggregate stats, leaderboard, release timeline, and benchmark coverage across every Valen model we track.
Check which of your devices can run this model and how fast.
Compare hosted per-token prices before you commit to local hardware.
Break-even math for self-hosting, renting a GPU, or paying per token.
Live status for the hosted APIs you might use instead of running this locally.
View on Hugging Face