GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
liskasYR
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
liskasYR
Model Tree
Input Modalities
Output Modalities
Supported Functionality
Model weights for the Nex-N2.5 family will be released as open source, alongside hosted online services.
We welcome developers and enterprises to integrate and try Nex-N2.5 and share their feedback.
We evaluate Nex-N2.5 across coding, agentic workflows, computer use, and multimodal understanding.
The tables below compare Nex-N2.5-mini, Nex-N2.5-Pro, and Nex-N2.5-Max with leading models across our evaluation suite.1, 2 Bold marks the best result in each benchmark, including ties; — indicates unavailable data.10
We also provide a prebuilt Docker image with our customized sglang fork preinstalled: nexagi/sglang:v0.5.18-nex-patch. The launch command is the same as above.
bash
# Multi-node (2 nodes, 16 x H200). Run the same command on every node with:# <node-rank> = 0 on the head node, 1 on the other node# <node0-ip> = IP of the head node (reachable from all others)docker run --gpus all --shm-size 32g --network host \-v /path/to/your/model:/model \nexagi/sglang:v0.5.18-nex-patch \python3 -m sglang.launch_server \--model-path /path/to/your/model \--trust-remote-code \--host 0.0.0.0 \--port 8000 \--nnodes 2 \--node-rank "${NODE_RANK}" \--dist-init-addr "${MASTER_ADDR}:5000" \--tp 16 \--pp-size 1 \--dp 1 \--ep-size 16 \--attention-backend dsv4 \--kv-cache-dtype fp8_e4m3 \--page-size 256 \--moe-a2a-backend deepep \--moe-runner-backend deep_gemm \--moe-dense-tp-size 1 \--deepep-mode auto \--context-length 262144 \--mem-fraction-static 0.84 \--chunked-prefill-size 8192 \--enable-mixed-chunk \--disable-overlap-schedule \--max-running-requests 64 \--cuda-graph-max-bs-decode 64 \--cuda-graph-backend-decode full \--cuda-graph-backend-prefill disabled \--chat-template /path/to/nex-n2.5-max/chat_template.jinja \--reasoning-parser deepseek-r1 \--tool-call-parser qwen3_coder
Single node with 8 × H100:
bash
docker run --gpus all --shm-size 32g --ipc=host \-p 30000:30000 \-v /path/to/your/model:/model \nexagi/sglang:v0.5.18-nex-patch \python3 -m sglang.launch_server \--model-path /model \--tp 8 \--host 0.0.0.0 --port 30000 \--reasoning-parser qwen3 \--tool-call-parser qwen3_coder \--chat-template /path/to/nex-N2.5-Pro/chat-template.jinja \--mamba-scheduler-strategy extra_buffer
Single node with 2 × H100:
bash
docker run --gpus all --shm-size 32g --ipc=host \-p 30000:30000 \-v /path/to/your/model:/model \nexagi/sglang:v0.5.18-nex-patch \python3 -m sglang.launch_server \--model-path /model \--tp 2 \--host 0.0.0.0 --port 30000 \--reasoning-parser qwen3 \--tool-call-parser qwen3_coder \--chat-template /path/to/nex-N2.5-mini/chat-template.jinja \--mamba-scheduler-strategy extra_buffer
For the best generation quality, we recommend the following sampling parameters:
temperature: 0.7top_p: 0.95top_k: 40Use reasoning_effort to control the thinking behavior of Nex-N2.5:
reasoning_effort | Mode | Behavior |
|---|---|---|
"none" | Non-thinking | Respond directly without a reasoning trace. |
"medium" (default) | Adaptive thinking | Let the model decide whether and how much to think before responding. |
"high" | Thinking | Always enable thinking before responding. |
For adaptive thinking, set reasoning_effort to "medium" in your OpenAI-compatible Chat Completions request. Replace <served-model-name> with the model name exposed by your server:
json
{"model": "<served-model-name>","messages": [{"role": "user", "content": "Explain how binary search works."}],"reasoning_effort": "medium"}
The chat template uses reasoning_effort; parameters such as enable_thinking and thinking_mode require gateway-specific translation.
Nex-series models support robust function-calling capabilities. To enable function calling, add the --tool-call-parser qwen3_coder flag when launching the server:
bash
python -m sglang.launch_server --model-path /path/to/your/model --tool-call-parser qwen3_coder
When the model produces a reasoning trace, configure SGLang to separate it from the final response:
--reasoning-parser qwen3--reasoning-parser deepseek-r1The deployment commands above include the appropriate reasoning parser and --tool-call-parser qwen3_coder. The parser extracts reasoning content; use reasoning_effort to select the thinking mode.