Laguna S 2.1 vs Ornith-1.5-122B

Laguna S 2.1

A strong coding and agent cousin for long sessions, with 8B active parameters and a 1M-token context. At 4-bit it needs a 96 to 128 GB machine, tight on a 128 GB one. The main risks are that nobody at Poolside answers its many reports, there are no safety results, and a build card misdescribes its file.

Ornith-1.5-122B

The largest Ornith that fits a 128 GB machine, a coding and terminal-agent cousin on Qwen3.5-122B-A10B's architecture with XML tool calls and 262,144 tokens of context. Its 4-bit builds need 84 to 93 GB. The main risk is an absent publisher, with no licence file, safety results or replies, and a card that misstates the hardware.

Laguna S 2.1

1. Quickest start is ollama run laguna-s-2.1, 96 GB for the default Q4_K_M, or the 66 GB nvfp4 tag on Apple Silicon
2. On our reference machine try llama-server -hf poolside/Laguna-S-2.1-GGUF:Q4_K_M --jinja -c 65536, from a llama.cpp release with the laguna architecture (b11772 has it). The 96 GB file leaves little room for context in 107.4 GB
3. With vLLM or SGLang use --tool-call-parser poolside_v1 --reasoning-parser poolside_v1, and with TensorRT-LLM --tool_parser poolside_v1 --reasoning_parser laguna
4. Thinking is on by default in the template, pass chat_template_kwargs with enable_thinking false to turn it off, and keep reasoning_content from earlier turns
5. The GGUFs ship set to 262,144 tokens. For 1M with llama.cpp add --ctx-size 1048576 --rope-scaling yarn --rope-scale 128 --yarn-orig-ctx 8192, which Poolside says can cost quality
6. Sampling per the generation config is temperature 1.0 and top_k 20, and Poolside suggests temperature 0.7 and top_p 0.95 at 1M
7. Expect occasional tool-schema slips in harnesses unlike Poolside's own, and validate JSON arguments, which Poolside lists as known limitations

Ornith-1.5-122B

1. Start it with ollama run ornith-1.5:122b-q4_K_M, or llama-server -hf ornith-ai/Ornith-1.5-122B-GGUF:Q4_K_M --jinja -c 262144
2. Budget about 92 GB for the Q4_K_M GGUF with a working context, and less context if the machine has under 100 GB for the model
3. 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
4. Thinking is on by default. Send chat_template_kwargs with enable_thinking false for short tasks, a switch the card doesn't mention
5. Pin which template your runtime loads, since chat_template.jinja keeps earlier reasoning and the tokenizer_config.json template drops it
6. Use temperature 0.6, top_p 0.95, top_k 20 for coding and temperature 1.0 for general tasks, as the card recommends
7. Add mmproj-Ornith-1.5-122B-BF16.gguf (0.9 GB) for image input in llama.cpp, and validate JSON output yourself, since structured output isn't documented