Ettore Di Giacinto 8134d6db37 docs(dllm): record Q4_K_M validation and quantization guidance ...

Q4_K_M validated on GB10: quality holds (cosine 0.9862, coherent
generation, 19/48 stopper exit) but a forward step is ~5x slower than
BF16 (27.5s vs 5.6s: native BF16 tensor cores vs K-quant MoE dequant).
Guidance: prefer BF16 when it fits; Q4_K_M is the memory-bound option.

Assisted-by: Claude Code (Fable 5)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

2026-06-11 19:22:02 +00:00

..

advanced

feat: forward reasoning_effort to the backend so jinja models honor it (#10184)

2026-06-05 13:45:43 +00:00

features

docs(dllm): record Q4_K_M validation and quantization guidance

2026-06-11 19:22:02 +00:00

getting-started

feat(cli): add interactive chat mode (#10226)

2026-06-09 14:58:44 +00:00

installation

feat(ui): Interactive model config editor with autocomplete (#9149)

2026-04-07 14:42:23 +02:00

reference

feat(cli): add interactive chat mode (#10226)

2026-06-09 14:58:44 +00:00

_index.md

docs: position LocalAI as a composable engine, not a bundle (#10136)

2026-06-02 17:34:43 +02:00

faq.md

docs: position LocalAI as a composable engine, not a bundle (#10136)

2026-06-02 17:34:43 +02:00

integrations.md

fix(anthropic): do not emit empty tokens and fix SSE tool calls (#9258)

2026-04-07 00:38:21 +02:00

overview.md

docs: architecture & feature diagrams (blueprint style) (#10137)

2026-06-02 18:43:22 +02:00

whats-new.md

docs: fix documentation typos (#10125)

2026-06-01 14:31:08 +02:00