Recipe: GLM-5.2 (unpruned QuantTrio Int4-Int8Mix) at 655,360-token context + MTP spec decode (DCP4, fp8_ds_mla) on a 4x NVIDIA DGX Spark (GB10) cluster
☆31Jul 13, 2026Updated 2 months ago
Alternatives and similar repositories for GLM-5.2-655K-MTP-4x-DGX-Spark---25-32tok-s
Users that are interested in GLM-5.2-655K-MTP-4x-DGX-Spark---25-32tok-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:
- 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 2 months ago
- Recipe: GLM-5.2 (unpruned QuantTrio Int4-Int8Mix) at 200K ctx with MTP spec decode on a 4x NVIDIA DGX Spark (GB10) cluster☆77Jul 25, 2026Updated last month
- MiMo-V2.5 Omni TP=2 on 2x DGX Spark · 1M context · NVFP4 4-bit KV (~1.97M-token KV pool @ 1M, ~30 tok/s) · 69-eval: thinking-OFF 97.8 bea…☆39Jul 13, 2026Updated 2 months 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…☆46Jul 13, 2026Updated 2 months ago
- 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…☆21Aug 17, 2026Updated 3 weeks ago
- 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.
- Live dashboard: fire N parallel streaming coding-agent runs at any OpenAI-compatible endpoint — per-run TTFT/tok-s/E2E, real kill switch,…☆26Jul 23, 2026Updated last month
- Autonomous self-improving 4x DGX Spark (GB10) MoA stack + LoRA loop (DSV4F router, Qwen3.6/Omni/TwoTower/Gemma). Hermes MoA routing, ~90%…☆22Aug 17, 2026Updated 3 weeks ago
- AEON vLLM Ultimate — vLLM 0.27.1 built from source for DGX Spark / Blackwell (sm_121a/GB10). DSpark quantized Markov heads, DFlash SWA on…☆143Updated this week
- DeepSeek-v4-Flash 0731 recipe for 2x DGX Sparks☆1,364Updated this week
- Self-contained DeepSeek V4 Flash DSpark TP=2 recipe for 2x DGX Spark with 62 tok/s benchmark☆24Jul 13, 2026Updated 2 months ago
- DeepSeek V4 Flash DSpark 1M NVFP4 KV recipe for 2x DGX Spark☆479Updated this week
- 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 2 months ago
- Run the AEON Bench suite on your own hardware: verified HuggingFace pull → serve → benchmark (text · agentic ×3 harnesses · vision · audi…☆25Updated this week
- Minimal Claude Code bootstrapper that installs an agent-architect for project-specific sub-agents.☆29Jul 1, 2026Updated 2 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.
- Testbench for llama.cpp llama-server☆15Aug 20, 2025Updated last year
- Uncensored/abliterated Ornith-1.0-35B (AEON Ultimate): 0% refusal, 0 coding-capability loss. BF16 + FP8 for vLLM.☆81Jun 29, 2026Updated 2 months ago
- Serve GLM-5.2 469B (REAP-pruned, NVFP4) across 3× NVIDIA DGX Spark with vLLM pipeline parallelism — 256K context, production-ready config…☆34Jul 12, 2026Updated 2 months ago
- Production-ready vLLM deployment wrapper for Qwen3.6-27B (NVFP4) — self-hosted OpenAI-compatible inference☆61Jul 30, 2026Updated last month
- Output high level Pcode (PcodeAST) in Ghidra☆17Apr 7, 2023Updated 3 years ago
- Automates Flatcam generation of G-code for my (and maybe your) PCB milling process☆10Jun 16, 2023Updated 3 years ago
- This repo helps to transform text into a better form for lora training☆12Apr 9, 2023Updated 3 years ago
- Second Brain is a desktop application that acts as a personal knowledge base, using retrieval-augmented generation (RAG), multimodal AI m…☆27Jan 30, 2026Updated 7 months ago
- Mixed-capability LLM benchmark for DGX Spark — 57 scenarios, 10 domains, partial-credit grading, trial statistics☆164Aug 29, 2026Updated 2 weeks ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- A task based orchestration TUI for oh-my-pi agent harness enabling highly parallel agentic development.☆26Feb 21, 2026Updated 6 months ago
- ☆17Jun 27, 2026Updated 2 months ago
- ☆39Jul 17, 2026Updated last month
- vLLM 0.25.1 serving stack for poolside/Laguna-S-2.1-NVFP4 with DFlash speculative decoding — DGX Spark & RTX 6000 PRO☆83Jul 22, 2026Updated last month
- Pipecat Guess Who?☆16Aug 1, 2025Updated last year
- Fused BF16 Huffman GEMV Inference kernel☆22Apr 22, 2026Updated 4 months ago
- KoboldCpp Smart Launcher with GPU Layer and Tensor Override Tuning☆30May 18, 2025Updated last year
- Generate Large Language Model text in a container.☆19Mar 24, 2023Updated 3 years ago
- Small program to run requests against a web server and look for problems☆11Jan 20, 2016Updated 10 years ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- ☆47Apr 29, 2026Updated 4 months ago
- ☆12Oct 28, 2023Updated 2 years ago
- ASAP smoothing☆13Sep 8, 2017Updated 9 years ago
- ☆15Aug 16, 2023Updated 3 years ago
- Local diagnostic CLI for NVIDIA DGX Spark (GB10). Detects power caps, UMA pressure, thermal risk, CUDA 13/SM_121 wheel mismatches, Docker…☆104Sep 5, 2026Updated last week
- A Claude Code plugin for a structured dev workflow — 14 expert agents, code review, planning, and task tracking, all from the terminal.☆17Updated this week
- Plan and delegate work to a scalable team of AI agents.☆19Feb 8, 2026Updated 7 months ago