Qwen3.5-2B vs ZAYA1-8B

Qwen3.5-2B

A small vision-language model for prototypes, fine-tuning and narrow local steps such as tool calls, tagging or reading an image. It runs in about 2 GB at 4 bits in six runtimes under plain Apache 2.0. Keep thinking off, since the card warns it loops. The card has no safety results, and Qwen has answered none of its discussions.

ZAYA1-8B

A small reasoning model trained from scratch by one lab, with a clean licence, 4-bit and FP8 builds and a team that answers questions. It's the hardest of the small models to run: its own architecture, a card that points at forks, and tool calling that needs a parser no release has. Little on limits, data or safety.

Qwen3.5-2B

1. Smallest start is ollama run qwen3.5:2b-q4_K_M (1.9 GB); plain qwen3.5:2b pulls the 2.7 GB Q8_0 build
2. Full precision vllm serve Qwen/Qwen3.5-2B --port 8000 --max-model-len 262144 --enable-auto-tool-choice --tool-call-parser qwen3_coder
3. Thinking is off by default; if you turn it on with "chat_template_kwargs": {"enable_thinking": true}, stream and cut off runaway output, since the card warns of thinking loops, and add --reasoning-parser qwen3 in vLLM or SGLang to split the reasoning out
4. There's no generation_config.json, so pass the card's sampling yourself, for example temperature=1.0, top_p=1.0, top_k=20, presence_penalty=2.0 for text without thinking
5. Use it for narrow steps or as a fine-tuning base, not as the main agent, as the card itself suggests
6. Validate any JSON it returns, since structured output isn't documented

ZAYA1-8B

1. Use it for reasoning, maths and code. Don't count on tool calling outside Zyphra's vLLM fork
2. Run it with Transformers 5.22.2 or SGLang 0.5.23, which have the model built in
3. Use temperature 1.0 and top_p 0.95 in general, and temperature 0.6 for agent and code work
4. Download Zyphra/ZAYA1-8B, not the legacy repository, for the released runtimes
5. The quantised repositories have no licence tag. The main one is Apache 2.0