Recipe: GLM-5.2 (unpruned QuantTrio Int4-Int8Mix) at 200K ctx with MTP spec decode on a 4x NVIDIA DGX Spark (GB10) cluster
☆66Jul 21, 2026Updated this week
Alternatives and similar repositories for GLM-5.2-QuantTrio-200K-4x-DGX-Spark--36tok-s
Users that are interested in GLM-5.2-QuantTrio-200K-4x-DGX-Spark--36tok-s are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Autonomous self-improving 4x DGX Spark (GB10) MoA stack + LoRA loop (DSV4F router, Qwen3.6/Omni/TwoTower/Gemma). Hermes MoA routing, ~90%…☆17Jul 5, 2026Updated 2 weeks ago
- Live dashboard: fire N parallel streaming coding-agent runs at any OpenAI-compatible endpoint — per-run TTFT/tok-s/E2E, real kill switch,…☆19Jul 8, 2026Updated 2 weeks ago
- 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…☆39Jul 13, 2026Updated last week
- Give any blind LLM eyes — on any machine — in one shot. Tiny local VLM (Qwen3.5-0.8B) as an OpenAI-compatible vision service. Mac (MLX) /…☆24Jul 7, 2026Updated 2 weeks ago
- ☆159Updated this week
- 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.
- DeepSeek V4 Flash DSpark 1M NVFP4 KV recipe for 2x DGX Spark☆148Updated this week
- Deploy DeepSeek V4 Flash (MoE reasoning model) on dual DGX Spark nodes with 1M token context, InfiniBand, and FP8 KV-cache☆80Jul 9, 2026Updated last week
- ☆15May 10, 2026Updated 2 months ago
- Working recipe to serve DeepSeek-V4-Flash across two NVIDIA DGX Spark (GB10) nodes with vLLM (TP=2, FP8 KV, MTP) over a RoCE/RDMA link — …☆57Jul 13, 2026Updated last week
- DeepSeek-V4-Flash-DSpark abliterated (uncensored) · ~100% refusal bypass · C1 ~57 tok/s · 1M ctx · 2× DGX Spark · HF weights☆22Jul 12, 2026Updated last week
- 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…☆20Jul 7, 2026Updated 2 weeks ago
- Mixed-capability LLM benchmark for DGX Spark — 57 scenarios, 10 domains, partial-credit grading, trial statistics☆135Jul 11, 2026Updated last week
- sparkDash ⚡ — Multi-DGX Spark Monitoring Dashboard☆62Updated this week
- Self-contained DeepSeek V4 Flash DSpark TP=2 recipe for 2x DGX Spark with 62 tok/s benchmark☆21Jul 13, 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.
- Uncensored/abliterated Ornith-1.0-35B (AEON Ultimate): 0% refusal, 0 coding-capability loss. BF16 + FP8 for vLLM.☆65Jun 29, 2026Updated 3 weeks ago
- Persistent JavaScript REPL for context manipulation, MCP integration, and focused sub-agent orchestration. A pi extension.☆24May 30, 2026Updated last month
- ☆16Feb 21, 2026Updated 5 months ago
- Production-ready vLLM deployment wrapper for Qwen3.6-27B (NVFP4) — self-hosted OpenAI-compatible inference☆47Jul 1, 2026Updated 2 weeks ago
- ☆71Jul 13, 2026Updated last week
- Open Source Desktop App to help with Previs for AI-native filmmaking — stage grey-box scenes, choreograph camera & cast with marks, expor…☆89Updated this week
- An attempt to reproduce CALM (Continuous Audio Language Models) using DACVAE as the audio VAE.☆17Feb 20, 2026Updated 5 months ago
- VENDORIZED in lucebox-hub. Fork of llama.cpp, ggml graph for lucebox inference engine☆31Jul 8, 2026Updated last week
- OpenCodeReview (Community Edition) - Agentic AI based source code review tool powered by NVIDIA NeMo Agent Toolkit. NVIDIA Hackathon Awar…☆16Sep 27, 2025Updated 9 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Homebridge plugin for Pentair IntelliCenter☆12Apr 13, 2023Updated 3 years ago
- This repo helps to transform text into a better form for lora training☆12Apr 9, 2023Updated 3 years ago
- my version of the models dev site which is way faster and has the filters I want☆18Apr 22, 2026Updated 3 months ago
- AEON vLLM Ultimate — vLLM 0.25.0 built from source for DGX Spark / Blackwell (sm_121a/GB10). One image serves the whole AEON fleet (Gemma…☆97Updated this week
- ☆12Feb 19, 2017Updated 9 years ago
- Fuzzing Infrastructure with k8s & cephfs☆12Jul 23, 2020Updated 5 years ago
- ☆18Jul 9, 2026Updated last week
- Spen's Official OpenOCD Mirror (no pull requests)☆12Jan 27, 2020Updated 6 years ago
- ☆12Jan 2, 2020Updated 6 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆23Dec 12, 2025Updated 7 months ago
- Ralph Wiggum loop extension for pi☆24Jun 30, 2026Updated 3 weeks ago
- Towards autonomous quantum physics research using LLM agents with access to intelligent tools☆18Feb 23, 2026Updated 4 months ago
- AI-driven discovery of new Gravitational Wave Detectors☆25Jan 10, 2024Updated 2 years ago
- Pure Rust Inference Engine☆607Updated this week
- Control panel for VLLM, Sglang, llama.cpp, exllamav3☆1,481Updated this week
- Fully uncensored, capability-enhanced abliteration of Qwen3.6-27B. NVFP4 + z-lab DFlash speculative decoding (n=12) on the unified ghcr.i…☆427Jul 3, 2026Updated 2 weeks ago