Inkling vs Qwen3.5-4B

Inkling

Thinking Machines' large multimodal generalist, stronger than Inkling-Small on factual recall by its own numbers. It needs about 710 GB of datacentre GPU memory even in NVFP4, so most agents will use a host such as Together AI or Tinker. The main risks are a use policy that binds on download and can change, and no outside safety results.

Qwen3.5-4B

A small vision-language cousin for tool calls, light agent steps and image or video reading on almost any machine, with switchable thinking. Ollama's 3.3 GB build or the 9.3 GB BF16 files run in every major runtime under plain Apache 2.0. The main risks are no safety results, no structured-output guarantee and no answers from Alibaba since March.

Inkling

1. Unless you have a multi-GPU Blackwell or H200 node, call it through Together AI, Fireworks, DeepInfra or Tinker rather than starting it
2. On 8 B200 GPUs, SGLang's recipe is sglang serve --trust-remote-code --model-path thinkingmachines/Inkling-NVFP4 --tp 8 --quantization modelopt_fp4 --enable-multimodal --reasoning-parser inkling --tool-call-parser inkling
3. Use the inkling tool parser, not Hermes, and the inkling reasoning parser
4. Pass reasoning_effort as none, minimal, low, medium, high (the default) or max, or a number from 0 to 0.99. The repository's template has no xhigh preset and raises an error for it, though Thinking Machines' docs list xhigh
5. Tool call arguments must reach the template as an object, not a JSON string, or it raises an error
6. Audio should be 16 kHz WAV, ideally under 20 minutes, and images 40 to 4096 px a side, per the card
7. Read the Model Acceptable Use Policy before deploying, it binds on download and bars some uses that are legal

Qwen3.5-4B

1. Smallest start is ollama run qwen3.5:4b (Q4_K_M, about 4 GB with context)
2. Full precision vllm serve Qwen/Qwen3.5-4B --port 8000 --max-model-len 262144 --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder
3. Turn thinking off with "chat_template_kwargs": {"enable_thinking": false} in the request body, since it's on by default and /think and /nothink aren't supported
4. There's no generation_config.json, so pass the card's sampling yourself, for example temperature=0.7, top_p=0.8, top_k=20, presence_penalty=1.5 without thinking
5. Keep the context at 128K or more if you rely on thinking, and turn on YaRN only past 262,144 tokens
6. Validate any JSON it returns, since structured output isn't documented