GLiDE decision model
GLiDE is Fastino's decision-model family in five sizes, from a 0.4B encoder to 27B. Inputs vary by checkpoint; weights use a community licence.
By Fastino · Weights repository upload: 19 Oct 2026
Fastino’s decision-model family spans 0.4B, 0.8B, 2B, 9B and 27B releases. Each returns option probabilities without generated reasoning. Inputs and serving behaviour vary: the 0.4B encoder and 9B release accept text or JSON and reject images; the original 27B entry supports images. Public weights use Fastino’s community licence, and Fastino also hosts a System One API.
Quick answers
What is GLiDE by Fastino?
GLiDE: Fastino’s decision-model family spans 0.4B, 0.8B, 2B, 9B and 27B releases.
Who makes GLiDE?
GLiDE: Fastino
Are GLiDE's weights open?
GLiDE: Weights on Hugging Face, or Fastino's hosted System One API Licence: Fastino community licence (not a standard open-source licence)
The smaller GLiDE releases
The 0.4B card reports a 7,999-token prompt limit and shortens longer inputs by keeping the first 1,024 tokens and the end. Its 6.9 ms median was measured on one RTX PRO 6000, with 1.77 GB peak GPU memory over the tested workload. The 9B package reports 7.94B actual parameters, a 40,000-token default limit and 18.92 GB peak GPU memory in its latency test. These are Fastino’s measurements on different checkpoints, not a general hardware-sizing rule.
Local runtimes and hardware limits
Facts
- Base and size
- 27B checkpoint: Qwen3.8-27B, 52.2 GB of bf16 weights, needs one 80 GB GPU. 0.4B: an Ettin encoder derivative, 0.81 GB of weights (1.77 GB tested peak GPU memory). 9B: 15.90 GB of weights (18.92 GB tested peak)
- Licence
- Fastino community licence (not a standard open-source licence)
- Access
- Weights on Hugging Face, or Fastino's hosted System One API
- Family
- Five sizes announced 5 Nov 2026: 0.4B, 0.8B, 2B, 9B and 27B
- Inputs
- Checkpoint-dependent: 0.4B and 9B accept text or JSON and reject images; original 27B supports images
Claims and sources
- Fastino says GLiDE 1.2 is #1 of 229 models on Decision Index 0.4.1 (as of 22 Oct 2026) vendor reportedsource
- In the index's public data (release 0.4.1, generated 22 Oct 2026), GLiDE 1.2 is first of 228 entries on the full score (71.52), ahead of jeffan-31b (69.75) and mammoth-1 (68.44); mammoth-1 leads both public-benchmark scores. In the index's 29 Oct data, GLiDE is second of 247, behind KnowLine 31B Gen1 (71.86) independentsource
Links
Source: Hugging Face → Source: API docs → Source: Decision Index → Source: Family announcement → Source: 0.4B card and weights → Source: 9B card and weights →
Other models by Fastino
JevBench scores and methodology
Related projects
No related projects are listed in the registry.