gpt-oss-20b VRAM & Memory Requirements
Specific checkpoints with sourced architecture and weight files. MXFP4 safetensors: 13.63 GiB–15.51 GiB at 8,192 tokens, 1 sequence, FP16 KV, vllm.
This result is an estimate, not a measured trace.Not verifiedFile-backed weights
Publisher and provenance
- PublisherOpenAI
- Hugging Face
openai/gpt-oss-20b - Revision
6cee5e81ee83917806bbde320786a8fb61efebee - Total parameters20,914,757,184
- Active parameters3,600,000,000
- Layers24
- Query heads64
- KV heads8 (sliding-window)
- Head dimension64
- Recorded context capability131,072
- Completenesscomplete · full
Active parameters describe tokens' routed compute, not the full resident model weight footprint. Full-resident weight estimates use total parameters.
Memory layers in this estimate
Artifact bytes, raw KV, engine extras, and total demand are separate. This is not a runtime trace.
- Weight artifact
- 12.82 GiB (13,761,264,768 bytes)
- Raw KV cache
- 0.19 GiB (204,472,320 bytes)
- Engine extras / workspace
- 0.63 GiB–2.51 GiB
- Total estimated demand
- 13.63 GiB–15.51 GiB
Published artifacts
| Quantization | Selected files | Bytes | Engine | Evidence |
|---|---|---|---|---|
| MXFP4 safetensors mxfp4 | model-00000-of-00002.safetensors, model-00001-of-00002.safetensors, model-00002-of-00002.safetensors | 13,761,264,768 (12.82 GiB / 13.76 GB) | vllm, unspecified | file-metadata |
| INT4 theoretical | No published file | 10,457,378,592 (theoretical) | — | theoretical |
Memory by quantization and context
Concurrent sequences = 1. KV defaults to FP16. The range includes documented runtime extras for the listed engine. These figures use the same core as the interactive calculator.
| Quantization | 2,048 tokens | 8,192 tokens | 32,768 tokens |
|---|---|---|---|
| MXFP4 safetensors | 13.49 GiB–15.37 GiB | 13.63 GiB–15.51 GiB | 14.19 GiB–16.09 GiB |
| INT4 theoretical Theoretical rows are not downloadable artifacts. | 9.91 GiB–13.18 GiB | 10.05 GiB–13.35 GiB | 10.62 GiB–14.05 GiB |
Raw KV contribution
Related pages
Sources
- gpt-oss-20b model card
- config.json — revision 6cee5e81ee83917806bbde320786a8fb61efebee
- safetensors index — metadata.total_size=13761264768
Assumptions that affect this result
- Requested context is within the recorded native window of 131072 tokens.
- Full-resident weight estimates use total parameters, including inactive MoE experts.
- This MoE lists 20914757184 total parameters and 3600000000 active parameters. Active-parameter compute is not used as the weight-residency figure.
- Weight bytes come from the selected weight files only, not from every file in the repository.
- Download file size is not peak GPU memory. Runtime layout, allocator padding, and KV are extra.
- Counted files: model-00000-of-00002.safetensors, model-00001-of-00002.safetensors, model-00002-of-00002.safetensors.
- Context budget is the number of cached tokens per sequence (prompt plus reserved generation).
- Concurrent sequences share one model replica; weights are not multiplied by sequence count.
Calculator
Loading catalog snapshot…
Search or pick a catalog checkpoint to see memory demand.
Search or pick a catalog checkpoint to see memory demand.