- Services
A decision method for frozen models served on vLLM: it fills typed fields from fixed choices by scoring single-token labels with the model’s existing output head. Independent fields run in parallel over a shared context. Decision Index measured it on a frozen Qwen3.8-27B.
A situational 27.78B-parameter dense decision model from kikoncuo. Treat the modality benchmarks above as the leading indicator of fit — composite scoring across modalities is still maturing. Newly released, so production-readiness is still being shaken out.
Generated from this model’s benchmarks and ranking signals. Editor reviews refine it over time.
The top devices for this model at 4-bit, ranked by fit and speed.
| Device | Grade | VRAM |
|---|---|---|
| Acer Veriton GN100 AI MiniAcer | SS | 17.5 GB |
| AMD Instinct MI300XAMD | SS | 17.5 GB |
| AMD Instinct MI325XAMD | SS | 17.5 GB |
| AMD Instinct MI355XAMD | SS | 17.5 GB |
| Apple M3 Ultra (32-core CPU, 80-core GPU)Apple | SS | 17.5 GB |
Explore the Provider
Aggregate stats, leaderboard, release timeline, and benchmark coverage across every kikoncuo model we track.
Cheapest current cloud rentals with at least 18 GB VRAM, refreshed hourly.
Advertising disclosure: we earn commissions when you shop through the links below.
| Option | Cost / GPU-hour |
|---|---|
NVIDIA GeForce RTX 3090Vast.ai · Spot · 24 GB VRAM | $0.08 |
NVIDIA RTX PRO 4000 BlackwellVast.ai · Spot · 24 GB VRAM | $0.11 |
NVIDIA RTX A5000Vast.ai · Spot · 24 GB VRAM | $0.11 |
NVIDIA GeForce RTX 3090Vast.ai · On-Demand · 24 GB VRAM | $0.12 |
NVIDIA RTX A6000Vast.ai · Spot · 48 GB VRAM | $0.13 |
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.
