- Status
- Verified
- Base model
- …
- Lineage
- …
- Unchanged from base
- …
- Trending
- #36
- Downloads, 30 days
- 877
- Weights
- 643 GB
- Revision
Official Website · Introduction · Model Downloads · Evaluation · Deployment · License
At a glance
- Parameters
- 321B, 288 experts, 8 active
- Architecture
- GLM 5 Next
- Context
- 1M tokens
- Precision
- BF16 100%
- Format
- Safetensors
- Released
- Nov 2026
- Updated
- Nov 2026
- Likes
- 17
- Downloads, all time
- 22
Architecture
- Layers
- 45
- Hidden size
- 4,096
- Attention
- 64 heads
- Experts
- 288 total, 8 active per token
- Vocabulary
- 154,880
- Positions
- 1,048,576
- Tied embeddings
- No
- Vision encoder
- glm5_next_vision
Run it
Pinned to the indexed revision.
hf download internlm/Sage-S2.1-Flash --revision 76f4513db7464485605a002a06a6190de0460574Through the hub: the same tools, each file from a source that is up (Hugging Face, ModelScope, IPFS), at this revision. The last line checks every file against the hash the tree names.
export HF_ENDPOINT=https://gethologram.ai
hf download internlm/Sage-S2.1-Flash --quiet && hf cache verify internlm/Sage-S2.1-FlashRead the full model card
Sage S2.1 Flash
Official Website · Introduction · Model Downloads · Evaluation · Deployment · License
Introduction
Sage S2.1 Flash is a scientific multimodal model from Shanghai Artificial Intelligence Laboratory designed for research tasks that require multiple rounds of analysis and verification. It combines scientific data understanding with information retrieval, programming, and tool use. It can use specialized software to perform analyses, check results against intermediate outputs and visual feedback, and adjust subsequent steps accordingly.

Through the unified representation architecture of Sage SciPerception, the model supports more than ten types of scientific input, including molecular graphs, crystal structures, and protein sequences and 3D structures. Features from each input type are encoded and projected into a shared representation space for reasoning alongside natural language instructions. These inputs support tasks such as prediction, classification, site localization, quantitative analysis, and structure inference.
Model Downloads
| Model | Hugging Face | ModelScope |
|---|---|---|
| Sage S2.1 Flash | Model repository | Model repository |
| Sage S2.1 Flash FP8 | Model repository | Model repository |
Evaluation Results

Highlights
Across the 15 benchmarks and six models shown in the chart, Sage S2.1 Flash placed first on four benchmarks and second on seven.
-
Machine learning engineering. Sage S2.1 Flash placed first on MLE-bench Lite with 90.3, ahead of DeepSeek-V4.1-Flash-1017 at 89.2.
-
Office and professional document processing. It placed first on OfficeQA Pro, Harvey LAB, and SpreadsheetBench 2, scoring 72.2, 25.0, and 37.1, respectively.
-
Tool use and research execution. It placed second on AutomationBench, ALE-CLI, BFCL V4, WebArena-Verified, DeepResearch Bench II, JobBench, and OSWorld-Verified.
Category Benchmark Sage S2.1 Flash GLM-5.3-Flash DeepSeek-V4.1-Flash-1017 Qwen3.8-Max GPT-5.6 Sol Claude Opus 5 Agentic Coding Terminal-Bench 2.1 87.9 84.3 87.6 89.6 86.2 90.2 DeepSWE 67.9 63.7 73.9 67.0 70.6 72.6 NL2Repo-Bench 57.2 53.0 62.7 63.2 60.7 79.9 SWE-bench Pro 60.6 60.3 61.8 65.3 59.8 76.5 Productivity SpreadsheetBench 2 37.1 32.4 35.8 34.9 32.7 33.6 ALE-CLI 32.4 28.1 35.4 24.8 28.6 29.5 APEX-Agents 61.7 50.8 69.2 66.3 55.4 61.3 GDPval 78.0 67.7 77.6 79.6 69.6 80.0 Workspace-Bench-Lite 67.1 65.1 66.8 67.4 57.4 68.1 Workspace-Bench 61.7 59.7 63.0 63.9 50.9 62.0 Tool Use OfficeQA Pro 72.2 64.7 69.7 66.2 66.4 67.2 Harvey LAB 25.0 20.0 11.7 24.2 5.0 22.7 AutomationBench 56.7 48.3 57.8 49.7 45.7 49.4 BFCL V4 75.5 71.7 71.4 66.8 68.8 80.6 JobBench 58.8 56.5 58.5 52.7 45.4 68.0 SkillsBench 62.3 58.3 52.8 66.7 62.5 63.7 τ³-bench Banking 45.4 39.2 47.4 55.2 46.9 48.7 ML Engineering MLE-bench Lite 90.3 84.3 89.2 82.2 80.7 88.0 PostTrainBench 39.2 36.8 – – 31.0 35.7 PaperBench 88.0 83.0 88.6 95.1 94.3 86.9 MLS-Bench 42.0 39.9 44.3 41.0 46.2 49.8 Deep Research DeepResearch Bench II 54.2 51.9 55.1 49.2 50.7 54.1 Search DeepSearchQA 94.4 92.6 95.3 – 93.2 – BrowseComp-VL 60.5 61.0 60.6 – – – WideSearch 81.5 77.2 86.3 81.9 83.3 84.0 BrowseComp 91.2 88.3 93.8 – 92.2 90.8 Vision OSWorld v2.1 69.3 66.4 70.1 66.4 70.4 74.0 OSWorld-Verified 85.2 83.5 78.5 84.3 82.2 86.4 WebArena-Verified 67.6 65.0 60.7 64.9 66.6 69.1 Vision2Web 78.0 75.8 – 75.2 73.5 80.2 WeaveBench 68.4 60.9 – 71.9 79.6 86.4 OSWorld-G 84.8 83.7 61.4 88.6 77.7 76.8 BabyVision 75.8 51.3 58.0 83.8 80.7 63.1
Deployment
Inference with Scientific Projectors
Sage SciPerception uses scientific encoders and trainable projectors to map scientific data into the language model's input embedding space, where the data can be processed alongside natural language instructions. The resulting representations preserve structural and local information from the original data for tasks such as materials property prediction, sequence classification, site localization, and structure inference.
Download the projector from the model repository and the shared loading scripts from Sage-SciPerception.
python -m pip install torch safetensors huggingface_hub
hf download internlm/Sage-S2.1-Flash --include "projectors/sage-s2.1-flash/**" --local-dir ./sage-s2.1-flash
hf download internlm/Sage-SciPerception load_projector.py modeling_projector.py --local-dir ./sage-s2.1-flash
cd sage-s2.1-flash
For a crystal structure task, you can first verify that the projector loads on the CPU.
from load_projector import load_projector
projector, config = load_projector(
"projectors/sage-s2.1-flash/cif/jarvis", device="cpu"
)
To generate a response, the client extracts features according to the relevant scientific input protocol and runs the projector. It combines the projector output with Sage S2.1 Flash's text token embeddings to form the complete prompt sequence, then passes it to the language model. Enable --enable-prompt-embeds on the vLLM server and send prompt_embeds to /v1/completions. Use the tokenizer and text embeddings that match the base model.
Set up the scientific encoders, task-specific scientific readouts, and preprocessing dependencies separately. See config.json for each task's input format. The Sage-SciPerception inference guide provides the full integration workflow and a CIF client example. Replace the example's projector path and base language model with the corresponding versions from this repository.
Inference for General Tasks
Use the following deployment guides for tasks such as coding, office productivity, security, and computer use.
License
The code and model weights in this repository are released under the MIT License.
Derived on Nov 16, 2026 from Hugging Face at revision 76f4513d, README.md , config.json . This model is not yet addressed, so its card comes from the main branch.
159 files, 643 GB. Every download is checked against its address.