docs(readme): refresh bundled LLM list to Qwen3.5/3.6
Some checks failed
check / cargo check (macos-latest) (push) Has been cancelled
check / cargo check (ubuntu-22.04) (push) Has been cancelled
check / cargo check (windows-latest) (push) Has been cancelled
check / svelte build + lint (push) Has been cancelled
audit / cargo audit (push) Has been cancelled
audit / npm audit (push) Has been cancelled

README LLM-formatting section now states four Qwen tiers (Qwen3.5 2B /
4B / 9B + Qwen3.6 27B) and the magnotia-llm crate row reflects the
four-tier registry. The whisper-ecosystem context doc gets the same
refresh and cites unsloth as the GGUF source.

Older roadmap and Phase-0 audit docs left untouched — they are dated
historical artefacts and rewriting them would muddy the audit trail.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-05-01 09:59:37 +01:00
parent 0f105f0e15
commit d234ef394e
2 changed files with 4 additions and 4 deletions

View File

@@ -78,9 +78,9 @@ Magnotia uses `whisper-rs` 0.16 with the `vulkan` feature ([crates/transcription
The `brief.md` references faster-whisper as a pattern source — treat it as one. Do not adopt it as a dependency.
### LLM runtime: `llama-cpp-2` with Qwen3 tiers
### LLM runtime: `llama-cpp-2` with Qwen3.5 / Qwen3.6 tiers
`crates/llm/` owns the LLM runtime. Three tiers (Qwen3 1.7B, Qwen3 4B-Instruct-2507, Qwen3 14B) selected via hardware probe. Resumable HTTP downloads with SHA-256 verification. Do not add alternative runtimes (candle, mistral.rs, etc.) without strong evidence — the current stack is working.
`crates/llm/` owns the LLM runtime. Four tiers (Qwen3.5 2B, Qwen3.5 4B, Qwen3.5 9B, Qwen3.6 27B) selected via hardware probe. All Q4_K_M GGUFs from unsloth's HF org. Resumable HTTP downloads with SHA-256 verification. Do not add alternative runtimes (candle, mistral.rs, etc.) without strong evidence — the current stack is working.
### GPU compatibility: Vulkan everywhere