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.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
AxionML
Model Tree
zai-org/GLM-5.3-Flash
Input Modalities
Output Modalities
Supported Functionality
| Architecture | Natively multimodal hybrid-attention MoE: KDA linear attention, DSA sparse attention with indexer, MLA, manifold-constrained hyper-connections |
| Total Parameters | 320B |
| Activated Parameters | 18B |
| Layers / Experts | 45 layers (3 dense + 42 MoE), 288 routed experts + shared expert, native MTP/NextN layer |
| Input | Text, image, video |
| Context Length | 1,048,576 tokens |
| Checkpoint Size | ~203 GB |
| Benchmark | Protocol | NVFP4 |
|---|---|---|
| GSM8K | Full 1,319 × 4 seeds | 97.14 |
| AIME 2026 | 30 × 16 × 4 seeds | 92.45 |
| Terminal-Bench 2.1 | 89 tasks, terminus-2, pass@1 | 83.1 |
Scores reported by RadixArk for this checkpoint (SGLang, 4x GB300, FP8 KV cache, NEXTN speculative decoding). Text-only evaluations.
gate_proj / up_proj / down_proj of all routed experts, the shared expert and the dense MLPs in layers 0–2lm_head; KV cache not quantized in the checkpoint (FP8 KV validated at serving time)cnn_dailymail samples, length 512bash
python3 -m sglang.launch_server \ --model-path AxionML/GLM-5.3-Flash-NVFP4 \ --quantization modelopt_fp4 \ --tp-size 4 \ --dsa-prefill-backend trtllm \ --dsa-decode-backend trtllm \ --kv-cache-dtype fp8_e4m3 \ --moe-runner-backend flashinfer_cutlass \ --speculative-algorithm NEXTN \ --speculative-num-steps 5 \ --speculative-eagle-topk 1 \ --speculative-num-draft-tokens 6 \ --speculative-adaptive \ --reasoning-parser glm45 \ --tool-call-parser glm47Use the lmsysorg/sglang:glm-5.3-flash image. Audit evidence (tensor-audit-b.json, precision-contract-b.json) is included in this repository.
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/GLM-5.3-Flash-NVFP4 \ --quantization modelopt_fp4 \ --tp-size 4 \ --dsa-prefill-backend trtllm \ --dsa-decode-backend trtllm \ --kv-cache-dtype fp8_e4m3 \ --moe-runner-backend flashinfer_cutlass \ --speculative-algorithm NEXTN \ --speculative-num-steps 5 \ --speculative-eagle-topk 1 \ --speculative-num-draft-tokens 6 \ --speculative-adaptive \ --reasoning-parser glm45 \ --tool-call-parser glm47