Head-to-head comparison of local LLMs for agentic workflows (Hermes Agent, tool-eval-bench)
☆34Jul 6, 2026Updated last month
Alternatives and similar repositories for Best-Local-Model_Agentic-Workflows_2026
Users that are interested in Best-Local-Model_Agentic-Workflows_2026 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Production-ready vLLM deployment wrapper for Qwen3.6-27B (NVFP4) — self-hosted OpenAI-compatible inference☆61Jul 30, 2026Updated last week
- llama-server start/stop scripts for Qwen3.6-35B-A3B UD-Q8_K_XL GGUF on DGX Spark☆27Jul 6, 2026Updated last month
- Run on TWO-DGX-Spark - vLLm-0.24.0 dual cache optimized DSV4F+DSpark+NVFP4 KV (Concurrency 12 with 1.5M context/3M KV token Pool) >0.58-0…☆21Jul 7, 2026Updated last month
- No-cloud Tailscale Mullvad exit-node toggle with CLI and SwiftBar menu bar UI☆33Jul 10, 2026Updated last month
- DeepSeek-v4-Flash 0731 recipe for 2x DGX Sparks☆626Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- MiniMax-M3 (428B, no pruning) at 36 tok/s on 2× NVIDIA DGX Spark — W4A16 GPTQ + NVFP4 KV + EAGLE-3 speculative decoding on vLLM. Three se…☆42Jul 13, 2026Updated last month
- sparkDash ⚡ — Multi-DGX Spark Monitoring Dashboard☆213Updated this week
- Deploy DeepSeek V4 Flash (MoE reasoning model) on dual DGX Spark nodes with 1M token context, InfiniBand, and FP8 KV-cache☆98Jul 9, 2026Updated last month
- Local diagnostic CLI for NVIDIA DGX Spark (GB10). Detects power caps, UMA pressure, thermal risk, CUDA 13/SM_121 wheel mismatches, Docker…☆101Jul 11, 2026Updated last month
- MiMo-V2.5 NVFP4 4-bit weights + NVFP4 4-bit KV cache + DFlash speculative decoding on 2× NVIDIA DGX Spark — 1M context, 3.4M-token KV poo…☆18Jul 13, 2026Updated last month
- malloc for memory-mapped files☆15Jun 25, 2020Updated 6 years ago
- DeepSeek V4 Flash DSpark 1M NVFP4 KV recipe for 2x DGX Spark☆363Updated this week
- Analog circuit simulation library; wrapper for ngspice☆11Aug 31, 2020Updated 5 years ago
- Portable Agent Skill to plan, spawn, review, and merge parallel CLI agents in isolated git worktrees, with deterministic Python/Bash runn…☆34Apr 12, 2026Updated 4 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Nim library for i18n and l10n☆11Aug 3, 2020Updated 6 years ago
- IKEA Home Smart library for Nim☆12Jun 8, 2022Updated 4 years ago
- Parse config by defining an object☆14Dec 23, 2025Updated 7 months ago
- An mmap-persistent Wolfe Garbe's SymSpell spell checking algorithm in Nim☆18Jun 18, 2026Updated last month
- yamaha dx7 synthesizer emulator using supercollider, Go, and the sc package☆13Sep 16, 2017Updated 8 years ago
- ☆13Feb 6, 2022Updated 4 years ago
- ☆12Nov 22, 2022Updated 3 years ago
- MLX Model Quantization Toolkit - Comprehensive collection of Jupyter notebooks for converting and quantizing large language models usi…☆16Aug 16, 2025Updated 11 months ago
- Cross-platform access to OS keyring☆16Feb 23, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- A small suite of apps that demonstrate how to code JACK MIDI applications.☆12Mar 6, 2013Updated 13 years ago
- DFlash vLLM for DGX Spark — Plug & Play Block-Diffusion Speculative Decoding☆54Jun 28, 2026Updated last month
- Gettext-like internationalisation module for Nim☆14Jan 4, 2021Updated 5 years ago
- Mixed-capability LLM benchmark for DGX Spark — 57 scenarios, 10 domains, partial-credit grading, trial statistics☆145Aug 2, 2026Updated last week
- SuperCollider wrapper for Omni.☆12Mar 29, 2024Updated 2 years ago
- ☆11Oct 8, 2021Updated 4 years ago
- Continuation-Passing Style for Nim 🔗☆15Apr 29, 2025Updated last year
- Recipe: GLM-5.2 (unpruned QuantTrio Int4-Int8Mix) at 200K ctx with MTP spec decode on a 4x NVIDIA DGX Spark (GB10) cluster☆73Jul 25, 2026Updated 2 weeks ago
- DeepSeek V4 Flash @ 1M token context on 2x NVIDIA DGX Spark — production-tested recipe (45 tok/s decode, real 800K prompts served)☆37Jul 13, 2026Updated last month
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Write Din-5008 letters in HTML☆14Mar 8, 2013Updated 13 years ago
- The Box of No Return is a Linux synth platform suitable for live musicianship, designed to handle patches with enormous demands.☆14Apr 15, 2023Updated 3 years ago
- A port of Python difflib to compute diffs and (re)highlight diff output intraline☆20Nov 4, 2025Updated 9 months ago
- Fixed point math support (via libfixmath) for the Nim programming language☆12Jun 16, 2016Updated 10 years ago
- Nim syslog module☆21Dec 27, 2019Updated 6 years ago
- A fork of nim's db_sqlite library based on ndb with proper typing☆15Apr 26, 2026Updated 3 months ago
- A high performance fork-join multi-threading library☆18Apr 25, 2017Updated 9 years ago