granite-3.2-2b-instruct
Support summary
granite-3.2-2b-instruct is a checkpoint published by IBM, built on the GraniteForCausalLM architecture. vLLM 0.28.0, the newest indexed vLLM release, documents support.
vLLM documents support in 20 of 20 indexed releases, from 0.17.0 to 0.28.0.
- Documented hardware
- CPU
- Documented quantization
- BF16
- Configured context
- 131,072 tokens
- License
- apache-2.0
Hardware, quantization and features count only statements about this checkpoint; engine-wide capabilities are listed with each release.
Hugging Face model card
- Publisher
- IBM
- Task
- text generation
- License
- apache-2.0
- Library
- transformers
- Architecture
- GraniteForCausalLM
- Weight tensor elements
- 2.5B
- Tensor types
- BF16
- Configured context
- 131,072 tokens
- Base models
- ibm-granite/granite-3.1-2b-instruct
- Weight access
- Public
- Repository created
- 2025-02-17
Model notes and sources
- vLLM v0.28.0 · docs/models/hardware_supported_models/cpu.md · 20 indexed revisions, v0.17.0 to v0.28.0
- ibm-granite/granite-3.2-2b-instruct · publisher model card
- ibm-granite/granite-3.2-2b-instruct · Hugging Face metadata
- ibm-granite/granite-3.2-2b-instruct · publisher configuration
- vllm · models/ibm-granite/granite-3.2-2b-instruct.yaml
- Reviewed
Engine support
3 engines
| Engine | Release | Checkpoint support | Evidence scope | Last known supported |
|---|---|---|---|---|
| vLLM | Version not pinnedRecipe / cookbook | Documented recipeSource: vllm · models/ibm-granite/granite-3.2-2b-instruct.yamlReviewed | View 0.28.0 | |
Features, dependencies and evidence for vLLM 0.28.0 | ||||
| SGLang | 0.5.19Newest indexed | No matching evidence curated | No supported release indexed | |
Features, dependencies and evidence for SGLang 0.5.19 | ||||
| TensorRT-LLM | 1.2.1Newest indexed | No matching evidence curated | No supported release indexed | |
Features, dependencies and evidence for TensorRT-LLM 1.2.1 | ||||