Test LLMs on real tasks. Compare models side-by-side.
☆394Jun 16, 2026Updated last month
Alternatives and similar repositories for BenchLocal
Users that are interested in BenchLocal are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆340May 15, 2026Updated 2 months ago
- DFlash block-diffusion speculative decoding running on Apple Silicon via MLX, with an ANE execution path that explores heterogeneous acce…☆62Apr 18, 2026Updated 3 months ago
- ☆67Jun 4, 2026Updated 2 months ago
- The best benchmark for LLMs on Apple's MLX framework knowledge and coding tasks.☆37Jun 12, 2026Updated last month
- MLX Model Quantization Toolkit - Comprehensive collection of Jupyter notebooks for converting and quantizing large language models usi…☆16Aug 16, 2025Updated 11 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- ☆32May 15, 2026Updated 2 months ago
- ☆36Mar 30, 2026Updated 4 months ago
- Find the hidden meaning of LLMs☆42Nov 13, 2025Updated 8 months ago
- Lossless DFlash speculative decoding for MLX on Apple Silicon☆759Jun 11, 2026Updated last month
- Minimalist repo to do mlx vlm constrained decoding in batch mode☆18Apr 11, 2026Updated 3 months ago
- LLM speculative inference server for consumer hardware & heterogeneous computing☆2,726Updated this week
- Control panel for VLLM, Sglang, llama.cpp, exllamav3☆1,621Updated this week
- Flash-MoE sidecar slot-bank runtime for large GGUF MoE models on Apple Silicon — llama.cpp fork☆119Jul 15, 2026Updated 3 weeks ago
- Moshi-Finetune-MLX lets you fine-tune Moshi (Native, Real-Time, Speech-to-Speech) models all on Apple Silicon.☆26Apr 21, 2026Updated 3 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- DFlash: Block Diffusion for Flash Speculative Decoding☆5,579May 10, 2026Updated 3 months ago
- Open source, clear, transparent, real world llm benchmarks☆57Updated this week
- Drop-in prompt-caching fixes for the LLM agent harness you use. Point your AI coding agent at this repo and it ships the patches.☆113Jul 10, 2026Updated last month
- REAP expert pruning for MoE LLMs on Apple Silicon via MLX☆58Mar 16, 2026Updated 4 months ago
- Tool-calling quality benchmark for LLM serving stacks. 80+ deterministic scenarios testing multi-turn orchestration, safety boundaries, a…☆285Updated this week
- Structured Chain-of-Thought☆219May 16, 2026Updated 2 months ago
- extract all your personal data history from cursor, codex, claude-code, windsurf, and trae☆847Jan 21, 2026Updated 6 months ago
- Adaptive Precision for EXpert Models: MoE-aware mixed-precision quantization☆431Jul 25, 2026Updated 2 weeks ago
- Repository for TRACE: Capability-Targeted Agentic Training☆112Jul 12, 2026Updated 3 weeks ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [ICLR 2026] ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference☆326Jul 1, 2026Updated last month
- Experimental llama.cpp fork for inference research and development☆731Updated this week
- Train Large Language Models on MLX.☆408Jul 21, 2026Updated 2 weeks ago
- vLLM Metal plugin powered by mlx-swift — high-performance LLM inference on Apple Silicon☆274Jun 3, 2026Updated 2 months ago
- 3x decode TPS increase On Qwen 3.6 27B @ temp 0.6 | Native MTP Speculative Decoding On Apple Silicon With No External Drafter.☆1,148Updated this week
- Benchmark to measure what the real knowledge cutoff of a model is☆16Jul 10, 2026Updated last month
- A simple, cross-platform CLI tool for quickly switching between Claude Code configuration profiles by managing different settings.json ve…☆16Jan 17, 2026Updated 6 months ago
- Exploratory stuff on RLMs for video workflows☆35Apr 20, 2026Updated 3 months ago
- Local AI workstation — discover, run, chat, benchmark, and generate images from open-weight models. DFlash/DDTree speculative decoding, T…☆24Aug 1, 2026Updated last week
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Run Claude Code against DeepSeek's Anthropic-compatible endpoint without touching your normal Claude config☆127Jun 25, 2026Updated last month
- llama-benchy - llama-bench style benchmarking tool for all backends☆623Jul 10, 2026Updated last month
- Exact speculative decoding on Apple Silicon, powered by MLX.☆382Apr 20, 2026Updated 3 months ago
- OpenClaw Operator gives coding agents like Codex and Claude Code the context and playbooks needed to set up, validate, and troubleshoot a…☆20Mar 7, 2026Updated 5 months ago
- 📊 LLM Context Benchmarks - A comprehensive benchmarking tool for testing LLMs with varying context sizes using Ollama. Features dual b…☆79Aug 2, 2026Updated last week
- KVarN, KV cache precision tail, low-bit quants in llama.cpp for longer context of better precision in the same VRAM☆842Updated this week
- The safest, simplest way to manage Hermes from your Mac. Pure SSH. No gateways, no exposed ports, no browser layer.☆1,986Jun 19, 2026Updated last month