gpt-oss-20b
Support summary
gpt-oss-20b is a checkpoint published by OpenAI, built on the GptOssForCausalLM architecture. The newest indexed releases vLLM 0.28.0 and SGLang 0.5.19 both document support. TensorRT-LLM lists its architecture, but not this exact checkpoint.
vLLM documents support in 20 of 20 indexed releases, from 0.17.0 to 0.28.0. SGLang documents support in 13 of 13 indexed releases, from 0.5.10 to 0.5.19.
- Documented hardware
- CPU, NVIDIA / CUDA, AMD / ROCm, and Intel GPU / XPU
- Documented quantization
- MXFP4
- Documented features
- Tensor parallelism and Tool calling
- 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
- OpenAI
- Task
- text generation
- License
- apache-2.0
- Library
- transformers
- Architecture
- GptOssForCausalLM
- Weight tensor elements
- 20.9B
- Tensor types
- BF16, U8
- Quantization
- mxfp4
- Configured context
- 131,072 tokens
- Weight access
- Public
- Repository created
- 2025-08-04
Model notes and sources
Do not transfer a 120B checkpoint claim to this 20B checkpoint; architecture evidence is shown separately.
- vLLM v0.28.0 · docs/models/supported_models.md · 20 indexed revisions, v0.17.0 to v0.28.0
- SGLang v0.5.19 · docs/docs/supported-models/generative_models.mdx · 3 indexed revisions, v0.5.17 to v0.5.19
- openai/gpt-oss-20b publisher metadata
- vLLM v0.28.0 · docs/models/hardware_supported_models/cpu.md
- vLLM v0.28.0 · docs/models/hardware_supported_models/xpu.md · 20 indexed revisions, v0.17.0 to v0.28.0
- SGLang v0.5.16 · docs_new/docs/supported-models/generative_models.mdx · 8 indexed revisions, v0.5.11 to v0.5.16
- SGLang v0.5.15.post1 · docs/supported_models/text_generation/generative_models.md · 9 indexed revisions, v0.5.10 to v0.5.15.post1
- openai/gpt-oss-20b · publisher model card
- openai/gpt-oss-20b · Hugging Face metadata
- openai/gpt-oss-20b · publisher configuration
- vllm · models/openai/gpt-oss-20b.yaml
- sglang · docs/cookbook/autoregressive/OpenAI/GPT-OSS.mdx
- vllm · OpenAI/GPT-OSS.md
- Reviewed
Engine support
3 engines
| Engine | Release | Checkpoint support | Evidence scope | Last known supported |
|---|---|---|---|---|
| vLLM | Version not pinnedRecipe / cookbook | Documented recipeSource: vllm · models/openai/gpt-oss-20b.yamlReviewed | View 0.28.0 | |
Features, dependencies and evidence for vLLM 0.28.0 | ||||
| SGLang | 0.5.19Newest indexed | Checkpoint evidenceSource: SGLang v0.5.19 · docs/docs/supported-models/generative_models.mdxReviewed | 0.5.19This release | |
Features, dependencies and evidence for SGLang 0.5.19 | ||||
| TensorRT-LLM | 1.2.1Newest indexed | Architecture listed; exact checkpoint unknown | No supported release indexed | |
Features, dependencies and evidence for TensorRT-LLM 1.2.1 | ||||