Granite 20B Code Instruct 8K is an open-source language model by ibm-granite. Features: 20b LLM, VRAM: 40GB, License: apache-2.0, Instruction-Based, Code Generating, LLM Explorer Score: 0.16.
| Model Type |
| |||||||||
| Use Cases |
| |||||||||
| Supported Languages |
| |||||||||
| Training Details |
| |||||||||
| Responsible Ai Considerations |
| |||||||||
| Release Notes |
|
| LLM Name | Granite 20B Code Instruct 8K |
| Repository 🤗 | https://huggingface.co/ibm-granite/granite-20b-code-instruct-8k |
| Base Model(s) | |
| Model Size | 20b |
| Required VRAM | 40 GB |
| Updated | 2026-07-27 |
| Maintainer | ibm-granite |
| Model Type | gpt_bigcode |
| Instruction-Based | Yes |
| Model Files | |
| Context Length | 8k |
| Generates Code | Yes |
| Model Architecture | GPTBigCodeForCausalLM |
| License | apache-2.0 |
| Model Max Length | 8192 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 49152 |
| Torch Data Type | bfloat16 |
| Activation Function | gelu |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Granite 20B Code Instruct | 0K / 40 GB | 10209 | 30 |
| Granite 20B Code Instruct R1.1 | 0K / 40 GB | 37 | 1 |