Ornith-1.5-397B vs Qwen3.5-4B

Ornith-1.5-397B

Ornith's flagship coding and terminal-agent cousin, with XML tool calls that vLLM and SGLang parse and 262,144 tokens of context. It needs about 290 GB even at 4 bits, so a multi-GPU server, not the 128 GB reference machine. The main risk is an absent publisher, with no licence file, no safety results and files replaced without a note.

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.

Ornith-1.5-397B

1. Start it with the card's vLLM command at --tensor-parallel-size 8, or ollama run ornith-1.5:397b on a machine with about 300 GB of memory
2. In vLLM pass --enable-auto-tool-choice --tool-call-parser qwen3_xml --reasoning-parser qwen3, and in SGLang --tool-call-parser qwen3_coder --reasoning-parser qwen3, so tool calls and reasoning come back parsed
3. Thinking is on by default. Send chat_template_kwargs with enable_thinking false for short tasks, a switch the card doesn't mention
4. Pin which template your runtime loads, since chat_template.jinja keeps earlier reasoning and the tokenizer_config.json template drops it
5. When downloading the NVFP4 build, fetch only the files its model.safetensors.index.json names (the 25-shard set, 241.7 GB), not the eight extra shards
6. Pin a revision when you download, since Ornith has replaced files in place
7. Validate JSON output yourself, since structured output isn't documented

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