Intern-S2-Mobius-FP8
Support summary
Intern-S2-Mobius-FP8 is a checkpoint published by InternLM, built on the InternS2MobiusForConditionalGeneration architecture. Official recipes or cookbooks cover SGLang, without pinning a stable release. vLLM lists its architecture, but not this exact checkpoint.
- Documented hardware
- NVIDIA / CUDA
- Documented quantization
- FP8
- Documented features
- Reasoning parsers and Speculative decoding
- Configured context
- 262,144 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
- InternLM
- Task
- image text to text
- License
- apache-2.0
- Library
- transformers
- Architecture
- InternS2MobiusForConditionalGeneration
- Weight tensor elements
- 36B
- Tensor types
- F32, BF16, F8_E4M3
- Quantization
- fp8
- Configured context
- 262,144 tokens
- Weight access
- Public
- Repository created
- 2026-08-04
Model notes and sources
Engine support
3 engines
| Engine | Release | Checkpoint support | Evidence scope | Last known supported |
|---|---|---|---|---|
| vLLM | 0.28.0Newest indexed | Architecture listed; exact checkpoint unknown | No supported release indexed | |
Features, dependencies and evidence for vLLM 0.28.0 | ||||
| SGLang | Version not pinnedRecipe / cookbook | Documented recipeSource 1: sglang · docs/cookbook/autoregressive/InternLM/Intern-S2-Mobius.mdxSource 2: sglang · docs/src/snippets/_deployment.jsxSource 3: sglang · docs/src/snippets/configs/internlm/intern-s2-mobius.jsxSource 4: sglang · docs/src/snippets/configs/internlm/intern-s2-mobius-benchmarks.jsxSource 5: sglang · docs/src/snippets/_playground.jsxReviewed | 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 | ||||