Decision models · Fastino
GLiDE 27B
- Task
- Classifying and extracting
- Returns
- Probability or score
- Precision tier
- 86 / 100
- Size
- 26B
- Max input
- 39K tokens
- License
- fastino-community
- Released
- 2026-10
What it decides
- Returns
- A probability for every option of each question you ask (one of up to 255 options, yes/no, or an ordered score), from one forward pass per question; it writes no text.
- Checks
- Routing, intent, triage, scoring and yes/no questions over text, JSON and images
- Languages
- Not stated on the card
- Precision
- 86 / 100 · 72.49 on the Decision Index 0.3.1 public suite, with a 112 ms median latency on one RTX PRO 6000 (model card).
- Clarity
- Probability or score (15 of 15 clarity points)
- How it runs
- Classifier head · reads the input once and writes nothing, so it answers in milliseconds.
- License
- fastino-community (Custom (read the terms))
How to run it
Original weights · Hugging Face
Full-precision files from Fastino, for Transformers, Sentence Transformers, Text Embeddings Inference, Infinity or vLLM.
Apps that run GLiDE 27B
Our pick for each kind of computer, assuming the model fits in its memory. Pick your own GPU or device in the Model Finder for an exact answer.
Mac (Apple silicon)
Windows PC, NVIDIA GPU
Windows PC, AMD Radeon
Linux, NVIDIA GPU
Linux server, 80 GB+ GPUs
| App | Type | Opens it as | Systems | Engine | Start |
|---|---|---|---|---|---|
| Sentence Transformers | Library | Original weights | macOSWindowsLinux |
|
Memory and speed
Each precision on an NVIDIA GeForce RTX 4090, for one decision on a 256-token input. The best hardware table below covers other systems and devices.
| Format | Memory needed | Time per decision | Decisions per second | Quality | Download |
|---|---|---|---|---|---|
Q8_0 | 34.6 GB | — | — | 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | All files (opens in a new tab) |
F16 | 59.1 GB | — | — | 86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | Original weights (opens in a new tab) |
Best hardware for GLiDE 27B
The least expensive GPU in our catalog that runs it without offloading is the AMD Radeon PRO W7800 48GB (launch price $2,799) at Q8_0.
| Quality | Hardware | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. |  NVIDIA RTX PRO 6000 Blackwell |
F16 | 59.3 GB / 96.0 GB | 97 ms | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. |  AMD Ryzen AI Max+ 395 (128 GB) |
Q8_0 | 34.8 GB / 96.0 GB | 201 ms | Runs well |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. |  NVIDIA GB10 (128 GB) |
Q8_0 | 34.8 GB / 115 GB | 329 ms | Runs well |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. |  NVIDIA RTX Spark N1X (6144-core GPU) (128 GB) |
Q8_0 | 34.8 GB / 102 GB | 354 ms | Runs well |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. |  AMD Instinct MI300X |
F16 | 59.3 GB / 192 GB | 86 ms | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. |  AMD Instinct MI325X |
F16 | 59.3 GB / 256 GB | 86 ms | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. |  AMD Instinct MI350X |
Q8_0 | 34.8 GB / 288 GB | 89 ms | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. |  AMD Radeon PRO W7900 |
Q8_0 | 34.8 GB / 48.0 GB | 100 ms | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. |  NVIDIA B200 |
F16 | 59.3 GB / 180 GB | 76 ms | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. |  NVIDIA GH200 Grace Hopper (96 GB GPU) |
F16 | 59.3 GB / 96.0 GB | 91 ms | Runs great |
Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.