Mellum2-12B-A2.5B-Thinking
Support summary
Mellum2-12B-A2.5B-Thinking is a checkpoint. SGLang 0.5.19, the newest indexed SGLang release, documents support. Official recipes or cookbooks cover vLLM, without pinning a stable release.
SGLang documents support in 4 of 13 indexed releases, from 0.5.16 to 0.5.19.
- Documented hardware
- NVIDIA / CUDA
- Documented quantization
- BF16
- Documented features
- Reasoning parsers and Tool calling
Hardware, quantization and features count only statements about this checkpoint; engine-wide capabilities are listed with each release.
Model notes and sources
- SGLang v0.5.19 · docs/docs/supported-models/generative_models.mdx · 3 indexed revisions, v0.5.17 to v0.5.19
- SGLang v0.5.16 · docs_new/docs/supported-models/generative_models.mdx
- vllm · models/JetBrains/Mellum2-12B-A2.5B-Thinking.yaml
- Reviewed
Engine support
3 engines
| Engine | Release | Checkpoint support | Evidence scope | Last known supported |
|---|---|---|---|---|
| vLLM | Version not pinnedRecipe / cookbook | Documented recipeSource: vllm · models/JetBrains/Mellum2-12B-A2.5B-Thinking.yamlReviewed | No supported release indexed | |
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 | No matching evidence curated | No supported release indexed | |
Features, dependencies and evidence for TensorRT-LLM 1.2.1 | ||||