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 serving lanes: speed / balanced / long-context.
☆46Jul 13, 2026Updated 2 months ago
Alternatives and similar repositories for MiniMax-M3-2x-DGX-Spark-36-tok-s
Users that are interested in MiniMax-M3-2x-DGX-Spark-36-tok-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 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
- 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
- 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
- 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
- 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
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Deploy DeepSeek V4 Flash (MoE reasoning model) on dual DGX Spark nodes with 1M token context, InfiniBand, and FP8 KV-cache☆106Aug 20, 2026Updated 3 weeks ago
- DeepSeek V4 Flash DSpark 1M NVFP4 KV recipe for 2x DGX Spark☆477Updated this week
- DeepSeek-v4-Flash 0731 recipe for 2x DGX Sparks☆1,350Updated this week
- DeepSeek-V4-Flash-DSpark abliterated (uncensored) · ~100% refusal bypass · C1 ~57 tok/s · 1M ctx · 2× DGX Spark · HF weights☆48Aug 17, 2026Updated 3 weeks ago
- 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 …☆31Jul 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
- llama-server start/stop scripts for Qwen3.6-35B-A3B UD-Q8_K_XL GGUF on DGX Spark☆27Jul 6, 2026Updated 2 months ago
- 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) /…☆29Jul 7, 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 — …☆82Jul 13, 2026Updated 2 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Profile repo — categorized index of NVFP4 model releases, DGX Spark inference stacks, Apple Silicon MLX builds, the voice-AI stack, and t…☆40Jul 9, 2026Updated 2 months ago
- Production-ready vLLM deployment wrapper for Qwen3.6-27B (NVFP4) — self-hosted OpenAI-compatible inference☆61Jul 30, 2026Updated last month
- Self-contained DeepSeek V4 Flash DSpark TP=2 recipe for 2x DGX Spark with 62 tok/s benchmark☆24Jul 13, 2026Updated 2 months ago
- ☆40Jul 17, 2026Updated last month
- Head-to-head comparison of local LLMs for agentic workflows (Hermes Agent, tool-eval-bench)☆34Jul 6, 2026Updated 2 months ago
- Local diagnostic CLI for NVIDIA DGX Spark (GB10). Detects power caps, UMA pressure, thermal risk, CUDA 13/SM_121 wheel mismatches, Docker…☆105Sep 5, 2026Updated last week
- Open Source Desktop App for Local-first pre-production canvas for AI video planning, prompts, assets, and handoff packages.uggested Donat…☆34Jul 20, 2026Updated last month
- 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
- ☆88Updated this week
- 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.
- sparkrun - launch, manage, and stop LLM inference workloads on NVIDIA DGX Spark systems. Live support: https://discord.com/invite/GH5kRg…☆505Updated this week
- Rust CLI for RBMEM (.rbmem), a structured Rust-Brain memory format with timestamp-protected sections, hierarchy, graph relations, Hermes …☆29Jun 14, 2026Updated 2 months ago
- sparkDash ⚡ — Multi-DGX Spark Monitoring Dashboard☆400Updated this week
- Uncensored/abliterated Ornith-1.0-35B (AEON Ultimate): 0% refusal, 0 coding-capability loss. BF16 + FP8 for vLLM.☆81Jun 29, 2026Updated 2 months ago
- Fully uncensored, capability-enhanced abliteration of Qwen3.6-27B. NVFP4 + z-lab DFlash speculative decoding (n=12) on the unified ghcr.i…☆462Jul 3, 2026Updated 2 months ago
- DFlash vLLM for DGX Spark — Plug & Play Block-Diffusion Speculative Decoding☆54Jun 28, 2026Updated 2 months ago
- Setup wizard for Hermes Gateway Desktop☆32Jul 2, 2026Updated 2 months ago
- Qwen3.5-122B-A10B on a DGX Spark with DFlash speculative decode. One-shot Docker/vLLM installer. 80+ tok/s!☆60Jun 29, 2026Updated 2 months ago
- Modified version of i.j Shell Property Sheets Export/Import 32☆11Nov 17, 2020Updated 5 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.
- OTel Plugin for Hermes Agent☆63Updated this week
- Mixed-capability LLM benchmark for DGX Spark — 57 scenarios, 10 domains, partial-credit grading, trial statistics☆164Aug 29, 2026Updated 2 weeks ago
- MIMIC: A privacy-first, local-first AI desktop assistant with VRM avatar integration, multi-model logic, and persistent persona memory. R…☆16Mar 3, 2026Updated 6 months ago
- Vim plugin to support file:// protocol with line/column support☆20Nov 24, 2022Updated 3 years ago
- VOICEROID plugin for Vim☆10Sep 2, 2026Updated last week
- My Notes from Hugging Face AI Agents Course☆21Feb 18, 2025Updated last year
- A pixel art space shooter built entirely by a 9B AI model on a single RTX 3060. Zero hand-written code.☆99Mar 19, 2026Updated 5 months ago