GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
truespirit
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
truespirit
Model Tree
ornith-ai/Ornith-1.5-397B
Input Modalities
Output Modalities
Supported Functionality
The checkpoint is tested with SGLang ROCm 7.2.4 on MI355X. AITER and native NEXTN/MTP are supported.
bash
docker run --rm \--device=/dev/kfd \--device=/dev/dri \--group-add video \--security-opt seccomp=unconfined \--ipc=host \--shm-size=32g \-p 8000:8000 \-v ~/.cache/huggingface:/root/.cache/huggingface \-e SGLANG_USE_AITER=1 \-e SGLANG_USE_AITER_UNIFIED_ATTN=1 \-e AITER_FLYDSL_FORCE=1 \-e SGLANG_MAMBA_SSM_DTYPE=bfloat16 \lmsysorg/sglang-rocm:v0.5.18-rocm724-mi35x-20260830 \python3 -m sglang.launch_server \--model-path truespirit/Ornith-1.5-397B-MXFP4 \--tp 1 \--attention-backend aiter \--page-size 16 \--reasoning-parser deepseek-r1 \--speculative-algorithm NEXTN \--speculative-num-steps 2 \--speculative-eagle-topk 1 \--speculative-num-draft-tokens 3 \--mem-fraction-static 0.95 \--max-running-requests 4 \--context-length 81920 \--host 0.0.0.0 \--port 8000
The server exposes an OpenAI-compatible API.
With the configuration above:
Results are serving benchmarks for this specific hardware/runtime configuration and are not model-quality benchmarks.
For general reasoning, temperature=0.6, top_p=0.95 is a useful starting point. For coding/agent workloads, temperature=1.0, top_p=0.95 is also suitable.
Only routed MoE expert weights (*.mlp.experts.*) were quantized to MXFP4. Components kept at higher precision follow the AMD Qwen3.5 MXFP4 recipe.
Quantization can cause numerical differences from the source FP8 checkpoint.
MIT, inherited from the base model. See the original ornith-ai/Ornith-1.5-397B model card for model details, intended use and limitations.