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.
☆42Jul 13, 2026Updated 3 weeks 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…☆38Jul 13, 2026Updated 3 weeks 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 3 weeks 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…☆20Jul 7, 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)☆36Jul 13, 2026Updated 3 weeks ago
- Deploy DeepSeek V4 Flash (MoE reasoning model) on dual DGX Spark nodes with 1M token context, InfiniBand, and FP8 KV-cache☆91Jul 9, 2026Updated 3 weeks ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- DeepSeek-v4-Flash 0731 recipe for 2x DGX Sparks☆322Updated this week
- DeepSeek V4 Flash DSpark 1M NVFP4 KV recipe for 2x DGX Spark☆240Updated this week
- DeepSeek-V4-Flash-DSpark abliterated (uncensored) · ~100% refusal bypass · C1 ~57 tok/s · 1M ctx · 2× DGX Spark · HF weights☆30Jul 12, 2026Updated 3 weeks ago
- Recipe: GLM-5.2 (unpruned QuantTrio Int4-Int8Mix) at 200K ctx with MTP spec decode on a 4x NVIDIA DGX Spark (GB10) cluster☆72Jul 25, 2026Updated last week
- 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…☆107Updated this week
- llama-server start/stop scripts for Qwen3.6-35B-A3B UD-Q8_K_XL GGUF on DGX Spark☆27Jul 6, 2026Updated 3 weeks 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 — …☆63Jul 13, 2026Updated 3 weeks ago
- vLLM 0.25.1 serving stack for poolside/Laguna-S-2.1-NVFP4 with DFlash speculative decoding — DGX Spark & RTX 6000 PRO☆75Jul 22, 2026Updated last week
- Profile repo — categorized index of NVFP4 model releases, DGX Spark inference stacks, Apple Silicon MLX builds, the voice-AI stack, and t…☆38Jul 9, 2026Updated 3 weeks ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Production-ready vLLM deployment wrapper for Qwen3.6-27B (NVFP4) — self-hosted OpenAI-compatible inference☆61Updated this week
- Self-contained DeepSeek V4 Flash DSpark TP=2 recipe for 2x DGX Spark with 62 tok/s benchmark☆23Jul 13, 2026Updated 3 weeks ago
- ☆36Jul 17, 2026Updated 2 weeks ago
- Local diagnostic CLI for NVIDIA DGX Spark (GB10). Detects power caps, UMA pressure, thermal risk, CUDA 13/SM_121 wheel mismatches, Docker…☆95Jul 11, 2026Updated 3 weeks ago
- Local benchmarking UI for LLMs and AI agents☆22Apr 13, 2026Updated 3 months ago
- sparkDash ⚡ — Multi-DGX Spark Monitoring Dashboard☆105Updated this week
- ☆79Updated this week
- sparkrun - launch, manage, and stop LLM inference workloads on NVIDIA DGX Spark systems☆421Updated this week
- Rust CLI for RBMEM (.rbmem), a structured Rust-Brain memory format with timestamp-protected sections, hierarchy, graph relations, Hermes …☆28Jun 14, 2026Updated last month
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- Uncensored/abliterated Ornith-1.0-35B (AEON Ultimate): 0% refusal, 0 coding-capability loss. BF16 + FP8 for vLLM.☆70Jun 29, 2026Updated last month
- Homomorphic Encryption Randomness Beacon☆13Dec 3, 2019Updated 6 years ago
- Fully uncensored, capability-enhanced abliteration of Qwen3.6-27B. NVFP4 + z-lab DFlash speculative decoding (n=12) on the unified ghcr.i…☆431Jul 3, 2026Updated last month
- Adaptation of babyagi in the Open AEA framework☆15May 11, 2023Updated 3 years ago
- DFlash vLLM for DGX Spark — Plug & Play Block-Diffusion Speculative Decoding☆54Jun 28, 2026Updated last month
- ☆28Feb 5, 2020Updated 6 years ago
- Setup wizard for Hermes Gateway Desktop☆30Jul 2, 2026Updated last month
- Qwen3.5-122B-A10B on a DGX Spark with DFlash speculative decode. One-shot Docker/vLLM installer. 80+ tok/s!☆54Jun 29, 2026Updated last month
- Modified version of i.j Shell Property Sheets Export/Import 32☆11Nov 17, 2020Updated 5 years 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.
- Mixed-capability LLM benchmark for DGX Spark — 57 scenarios, 10 domains, partial-credit grading, trial statistics☆138Updated this week
- Load balancer for your Claude Pro/Max subscription accounts.☆16Apr 13, 2026Updated 3 months ago
- MIMIC: A privacy-first, local-first AI desktop assistant with VRM avatar integration, multi-model logic, and persistent persona memory. R…☆15Mar 3, 2026Updated 5 months ago
- Vim plugin to support file:// protocol with line/column support☆20Nov 24, 2022Updated 3 years ago
- VOICEROID plugin for Vim☆10Jan 14, 2019Updated 7 years ago
- Fix the focus and the size of windows in Vim☆17Mar 21, 2022Updated 4 years ago
- Tool-calling quality benchmark for LLM serving stacks. 80+ deterministic scenarios testing multi-turn orchestration, safety boundaries, a…☆277Updated this week