Granite 20B Code Instruct is IBM's language model. IBM's 20B-parameter code-specialized Granite model fine-tuned for instruction following, logical reasoning, and problem-solving in programming tasks with an 8K context window.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Cheapest Instances to Run It
Cloud GPU instances that can host Granite 20B Code Instruct, ranked by cheapest on-demand price. The model needs about 48 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
Instance | Cloud | GPU | VRAM | Price | Cheapest region | |
|---|---|---|---|---|---|---|
| Standard_NP10s | AMD Alveo U250 FPGA (64GB) | 64 GB | $1.65/hr | |||
| Standard_NV32as_v4 | AMD Radeon Instinct MI25 | 64 GB | $1.86/hr | |||
| g2-standard-24 | 2× nvidia-l4 | 48 GB | $1.99/hr | |||
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Granite 4.2 8B | 131K | $0.060 | $0.150 | Available | |
| Granite 4.1 8B | 131K | $0.050 | $0.100 | Deprecated | |
| Granite 4 Micro H | 131K | — | — | Available | |
| Granite 4.2 30B | — | 131K | — | — | Available |
| Granite 4.2 3B | — | 131K | — | — | Available |
| Granite 4 350M | — | — | — | — | Available |
| Granite 4 350M H | — | — | — | — | Available |
| Granite 4 H Micro | — | — | — | — | Available |
| Granite 4 H Small | — | — | — | — | Available |
| Granite 4 H Tiny | — | — | — | — | Available |
| Granite 20B Code Instruct | — | — | — | — | Current |