GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
SwarmDo
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
SwarmDo
Model Tree
Qwen/Qwen3.6-27B
Input Modalities
Output Modalities
Supported Functionality
Pre-merged, ready-to-serve weights of SwarmDo-A2. The
combined coding + render-verified visual-coding adapter is already merged into Qwen/Qwen3.6-27B with the
vision tower intact, so you can serve it directly with vLLM — no merge step needed.
bash
vllm serve SwarmDo/SwarmDo-A2-merged --served-model-name swarmdo-a2 \--enable-auto-tool-choice --tool-call-parser qwen3_xml --reasoning-parser qwen3 \--enforce-eager --trust-remote-code
Then call it as an OpenAI-compatible chat endpoint (model = "swarmdo-a2"); pass an image via the standard
image_url block for visual-coding (image → code).
One model, both skills — fixes real bugs (execution-verified) and writes code from images (render-verified), with measured proof that combining the two degrades neither (the "churn gate").
a2/)Notes: serve as these merged weights (native fast path). Do not load A2 as a vLLM LoRA — the adapter reaches the base's gated-DeltaNet modules, which JIT-hang under vLLM's LoRA path. There is no text GGUF for A2 (quantizing to GGUF drops the vision tower). Apache-2.0.