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
poolside/Laguna-XS-2.1
Input Modalities
Output Modalities
Supported Functionality
| Architecture | MoE; 40 layers (10 global attention + 30 sliding-window), sigmoid-gated attention |
| Total Parameters | 33B |
| Activated Parameters | 3B |
| Context Length | 262,144 tokens |
| Checkpoint Size | ~22 GB |
| Benchmark | BF16 | NVFP4 |
|---|---|---|
| SWE-bench Verified | 70.85 ± 0.85 | 68.95 ± 0.90 |
| SWE-bench Multilingual | 63.17 ± 1.42 | 61.83 ± 1.42 |
| SWE-Bench Pro (Public) | 47.61 ± 0.96 | 47.06 ± 0.96 |
| Terminal-Bench 2.0 | 37.53 ± 2.81 | 37.08 ± 2.47 |
Scores reported by Poolside for this checkpoint (mean pass@1, Harbor framework).
nvfp4-pack-quantized, group size 16) on routed and shared expert MLPs; Poolside's official NVFP4 releasebash
python3 -m sglang.launch_server \ --model-path AxionML/Laguna-XS-2.1-NVFP4 \ --trust-remote-codebash
vllm serve AxionML/Laguna-XS-2.1-NVFP4 \ --enable-auto-tool-choice \ --tool-call-parser poolside_v1 \ --reasoning-parser poolside_v1Quantization is detected automatically in vLLM, SGLang (sgl-project/sglang#24204) and Transformers. The FP8 KV cache needs vLLM ≥ 0.22.0; tool calling needs a vLLM build with vllm#47311 (otherwise use --tool-call-parser glm47).
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.
python3 -m sglang.launch_server \ --model-path AxionML/Laguna-XS-2.1-NVFP4 \ --trust-remote-codevllm serve AxionML/Laguna-XS-2.1-NVFP4 \ --enable-auto-tool-choice \ --tool-call-parser poolside_v1 \ --reasoning-parser poolside_v1