GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
AxionML
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
AxionML
Model Tree
thinkingmachines/Inkling-Small
Input Modalities
Output Modalities
Supported Functionality
| Architecture | 42-layer decoder-only multimodal MoE; hybrid local/global attention |
| Total Parameters | 276B |
| Activated Parameters | 12B |
| Experts | 256 routed (6 active) + 2 shared |
| Input | Text, image, audio (16 kHz WAV) |
| Checkpoint Size | ~171 GB |
| Benchmark | Inkling-Small |
|---|---|
| SWE-bench Verified | 80.2 |
| SWE-bench Pro (Public) | 55.9 |
| Terminal-Bench 2.1 (best harness) | 64.7 |
| SciCode | 48.7 |
| GDPval-AA v2 | 1269 |
| MCP Atlas (public) | 79.6 |
| BrowseComp (w/ context) | 77.4 |
| Toolathlon Verified | 54.4 |
| GPQA Diamond | 89.5 |
| HLE (text only) | 31.6 |
| HLE (with tools) |
Scores are from the Inkling-Small model card (full-precision baseline).
bash
python3 -m sglang.launch_server \ --model-path AxionML/Inkling-Small-NVFP4 \ --tp 4 \ --trust-remote-codebash
vllm serve AxionML/Inkling-Small-NVFP4 \ --tensor-parallel-size 4 \ --trust-remote-codeMinimal commands; for tuned serving flags follow the official recipes: SGLang, vLLM, TokenSpeed.
The base model was trained on data that may contain toxic language and societal biases. The quantized model inherits these limitations. It may generate inaccurate, biased, or offensive content. Please refer to the original model card and the upstream quantized model card for full details.
| 47.8 |