Autotune
Time to first token is 39% faster Agent wall times decrease by 46% No swaps Tracks your resource usage in real-time and adjusts how the model runs so that it works perfectly on your device. Implements KV cache sizing, prefix caching, live RAM pressure management, context trimming, KV quantization, and more. Built a ton of features 10k downloads and climbing consider using it and giving it a star :)
Autotune launched on May 5, 2026 with 8 votes, #1,430 of 20,538 launches that month and more than 90% of that year's launches.
What it does
Autotune is an open-source runtime optimizer for local LLMs that reduces KV cache memory, improves first-token latency, and dynamically adapts inference settings to your hardware and workload. It works with Ollama, MLX, and as an API. Results from benchmarks show that Autotune can lower time-to-first-token by 39%, wall time for agentic workflows by 46%, and KV cache memory usage by 67%. Features include an OpenAI-compatible local API, a built-in CLI, RAM management, and model recommendations.
autotune frees 300+ MB of RAM per request and cuts response time by up to 53%. Drop-in wrapper for Ollama. One pip install, no config.
autotune sits between your code and Ollama and applies automatic optimizations: right-sized KV buffers, KV precision tuning, system prompt caching, intelligent context management, and model keep-alive. The result: 300+ MB freed per request, first word up to 53% faster , and your computer stays responsive. No config changes. Your code stays exactly the same. autotune sits between your code and Ollama as a transparent proxy. Before each request reaches Ollama, autotune calculates the exact memory it needs, watches live RAM usage from your other apps, and adjusts automatically. No config. No changes to your code or output quality. Every time Ollama runs your prompt, it must first allocate a…from autotunellm.com
Does a similar job
all alternatives →
80% faster, 50% less memory, 0% loss of accuracy Llama finetuning2023 · github.com · ▲385Hi HN! I'm just sharing a project I've been working on during the LLM Efficiency Challenge - you can now finetune Llama with QLoRA 5x faster than Huggingface's original implementation on your own local GPU. Some highlights: 1. Manual autograd engine - hand derived backprop steps. 2. QLoRA / LoRA 80% faster, 50% less memory. 3. All kernels written in OpenAI's Triton language. 4. 0% loss in accuracy - no approximation methods - all exact. 5. No change of hardware necessary. Supports NVIDIA GPUs since 2018+. CUDA 7.5+. 6. Flash Attention support via Xformers. 7. Supports 4bit and 16bit…
I put an AI agent on a $7/month VPS with IRC as its transport layerMar 2026 · georgelarson.me · ▲340The stack: two agents on separate boxes. The public one (nullclaw) is a 678 KB Zig binary using ~1 MB RAM, connected to an Ergo IRC server. Visitors talk to it via a gamja web client embedded in my site. The private one (ironclaw) handles email and scheduling, reachable only over Tailscale via Google's A2A protocol. Tiered inference: Haiku 4.5 for conversation (sub-second, cheap), Sonnet 4.6 for tool use (only when needed). Hard cap at $2/day. A2A passthrough: the private-side agent borrows the gateway's own inference pipeline, so there's one API key and one billing relationship…
Context GatewayMar 2026 · github.com · ▲220We built an open-source proxy that sits between coding agents (Claude Code, OpenClaw, etc.) and the LLM, compressing tool outputs before they enter the context window. Demo: https://www.youtube.com/watch?v=-vFZ6MPrwjw#t=9s. Motivation: Agents are terrible at managing context. A single file read or grep can dump thousands of tokens into the window, most of it noise. This isn't just expensive — it actively degrades quality. Long-context benchmarks consistently show steep accuracy drops as context grows (OpenAI's GPT-5.4 eval goes from 97.2% at 32k to 36.6% at 1M…
- ATA tool to benchmark LLM APIs (OpenAI, Claude, local/self-hosted)2025 · llmapitest.com · ▲55
I recently built a small open-source tool to benchmark different LLM API endpoints — including OpenAI, Claude, and self-hosted models (like llama.cpp). It runs a configurable number of test requests and reports two key metrics: • First-token latency (ms): How long it takes for the first token to appear • Output speed (tokens/sec): Overall output fluency Demo: https://llmapitest.com/ Code: https://github.com/qjr87/llm-api-test The goal is to provide a simple, visual, and reproducible way to evaluate performance across different LLM providers, including…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 29d ago · world.pixverse.video
Source: Product Hunt launch ↗
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
🌱 Private, quiet space for thinking. Simple app for .md files. - zakirullin/files.md
Dev tools · May 2026 · github.com