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-S-2.1
Input Modalities
Output Modalities
Supported Functionality
| Architecture | MoE; 48 layers (12 global attention + 36 sliding-window, window 512), softplus-gated attention |
| Total Parameters | 117.6B |
| Activated Parameters | 8.5B |
| Experts | 256 + 1 shared |
| Context Length | 1,048,576 tokens |
| Checkpoint Size | ~100 GB |
| Benchmark | Laguna S 2.1 |
|---|---|
| Terminal-Bench 2.1 | 70.2 |
| SWE-bench Multilingual | 78.5 |
| SWE-Bench Pro (Public) | 59.4 |
| DeepSWE | 40.4 |
| SWE Atlas (Codebase QnA) | 46.2 |
| Toolathlon Verified | 49.7 |
Scores are from the Laguna S 2.1 model card.
nvfp4-pack-quantized, group size 16) on routed-expert gate_proj / up_proj / down_proj; Poolside's official NVFP4 release, calibrated at the 1M-context configurationbash
# Poolside notes NVFP4 does not currently run correctly on SGLang; use vLLM below.bash
vllm serve AxionML/Laguna-S-2.1-NVFP4 \ --enable-auto-tool-choice \ --tool-call-parser poolside_v1 \ --reasoning-parser poolside_v1 \ --max-model-len 262144Requires vLLM ≥ 0.25.0; quantization is detected automatically. Optional DFlash speculative decoding: add --speculative-config '{"model":"poolside/Laguna-S-2.1-DFlash-NVFP4","num_speculative_tokens":7,"method":"dflash"}' --max-num-seqs 32. Serve with the sampling defaults in generation_config.json.
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.
vllm serve AxionML/Laguna-S-2.1-NVFP4 \ --enable-auto-tool-choice \ --tool-call-parser poolside_v1 \ --reasoning-parser poolside_v1 \ --max-model-len 262144