From 9a2f989cdd6a1498616610a613f68845bb0635bf Mon Sep 17 00:00:00 2001 From: Asher Feldman <59994+asher@users.noreply.github.com> Date: Sun, 9 Aug 2026 23:31:05 -0700 Subject: [PATCH 1/2] docs(readme): cleanup --- README.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 6115657..e2f73e0 100644 --- a/README.md +++ b/README.md @@ -10,8 +10,8 @@ or your browser, serve it over OpenAI- and Anthropic-compatible APIs, connect your coding agent to it, talk to it by voice, build a local RAG stack on it, and fine-tune it with LoRA. One command, entirely on your Mac. -It runs the community's K-quant and IQ-quant GGUF builds — size for size, -the most accurate open quant formats there are — exactly as published +It runs the community's K-quant and IQ-quant GGUF builds - size for size, +the most accurate open quant formats available - exactly as published ([accuracy per byte](#accuracy-per-byte)). The companion project [mlx-kquant](https://github.com/asher/mlx-kquant) supplies the Metal kernels that run these formats natively on Apple's @@ -323,7 +323,7 @@ flowchart TB serve --> aux["embeddings + rerank
STT + TTS"] ``` -Serving-side mechanics — engine, batching, and the HTTP layers: +Serving-side mechanics - engine, batching, and the HTTP layers: [docs/serving-architecture.md](https://github.com/asher/gmlx/blob/main/docs/serving-architecture.md). ## Python API From 18745ebfb8d195c5656918bd21694fb040956a8b Mon Sep 17 00:00:00 2001 From: Asher Feldman <59994+asher@users.noreply.github.com> Date: Sun, 9 Aug 2026 23:36:01 -0700 Subject: [PATCH 2/2] chore(readme): cleanup --- README.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index e2f73e0..bf17c4c 100644 --- a/README.md +++ b/README.md @@ -10,9 +10,9 @@ or your browser, serve it over OpenAI- and Anthropic-compatible APIs, connect your coding agent to it, talk to it by voice, build a local RAG stack on it, and fine-tune it with LoRA. One command, entirely on your Mac. -It runs the community's K-quant and IQ-quant GGUF builds - size for size, -the most accurate open quant formats available - exactly as published -([accuracy per byte](#accuracy-per-byte)). The companion project +It runs the community's K-quant and IQ-quant GGUF builds exactly as +published. Size for size, these are the most accurate open quant formats +available ([accuracy per byte](#accuracy-per-byte)). The companion project [mlx-kquant](https://github.com/asher/mlx-kquant) supplies the Metal kernels that run these formats natively on Apple's [MLX](https://github.com/ml-explore/mlx) framework. On the same file, gmlx