Serve DeepSeek-V4-Flash (NVFP4) on 2x RTX PRO 6000 (SM120) with working MTP speculative decoding (+38% single-stream). Root-cause fix: MTP draft experts are MXFP4, routed to Mxfp4MoEMethod.
☆18Jun 25, 2026Updated 4 months ago
Alternatives and similar repositories for dsv4-flash-nvfp4-sm120
Users that are interested in dsv4-flash-nvfp4-sm120 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Concurrency Patch to enable on DSpark - DeepSeek V4 Flash/Pro C=16 can be modified for more☆12Jun 29, 2026Updated 4 months ago
- ☆14May 2, 2026Updated 6 months ago
- Terminal braille rendering library for images, animation, and expressive CLI graphics.☆12Updated this week
- keys-latest: GLM-5.2 QuantTrio INT4/INT8 ablit + DFlash · 4x DGX Spark · k=12 · 128k · seqs=4 · KV 10GiB☆14Aug 17, 2026Updated 2 months ago
- A tiny Java program that shows the current calendar week in a system tray☆11Sep 2, 2017Updated 9 years 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.
- Simple package installer for install and runs Syncthing as Windows Service (without tray utility - runs hidden)☆11May 28, 2017Updated 9 years ago
- DICE: Diffusion Large Language Models Excel at Generating CUDA Kernels☆13Jun 8, 2026Updated 5 months ago
- Keep 10% of a model, match it, and let it keep learning, without training its weights.☆16Updated this week
- Tested MiaAI-based DeepSeek V4 Flash speed profile for two ASUS GX10s: pinned patch, settings, and benchmark helper.☆15Sep 5, 2026Updated 2 months ago
- Supply-chain auditor for (abliterated) GGUF & .safetensor models: chat-template tamper detection, tensor fingerprints, plain-language rep…☆12Oct 15, 2026Updated 3 weeks ago
- GB10 NVFP4 native MTP reproducibility pack for Qwen3.6-35B-A3B☆13May 19, 2026Updated 5 months ago
- GBIF Alert is a GBIF occurrence based alert system.☆11Updated this week
- 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 3 months ago
- Pinescript Editor Background .XML and Language.XML for Notepad++☆13Dec 4, 2019Updated 6 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- DeepSeek-V4-Flash-DSpark abliterated (uncensored) · ~100% refusal bypass · C1 ~57 tok/s · 1M ctx · 2× DGX Spark · HF weights☆58Aug 17, 2026Updated 2 months ago
- Break a PDF into chapters with metadata. Creates a folder with the chapters properly labeled. Do the Truffle Shuffle!☆21Updated this week
- ☆28Sep 27, 2026Updated last month
- PolarGrad: A Class of Matrix-Gradient Optimizers from a Unifying Preconditioning Perspective☆18Aug 10, 2026Updated 3 months ago
- A proxy for minimax-m2, enabling interleaved thinking, and tool calls.☆38Nov 21, 2025Updated 11 months ago
- ☆25Jun 24, 2026Updated 4 months ago
- ☆23Updated this week
- A Qt GUI interface and build system for QuantConnect's Lean☆20Apr 5, 2021Updated 5 years ago
- A safety gate for DeepSeek Harness: a stronger model reviews dangerous tool calls before they run. Plus vision and BlockRun's full model …☆18Sep 5, 2026Updated 2 months 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.
- My collection of dotfiles☆14Nov 4, 2026Updated last week
- RIVF 2021: Deep neural network based learning to rank for address standardization☆10Jul 13, 2024Updated 2 years ago
- Open quantization tooling for TurboQuant-style low-bit LLM releases, stock GGUF deployment, and Apple Silicon runtime experiments.☆10May 5, 2026Updated 6 months ago
- A collection of C# projects translated from Adrian Rosebrock excellent python examples using OpenCV☆12Feb 24, 2017Updated 9 years ago
- OFD（开放版式文档，GB/T 33190—2016）解析、校验与渲染工具集 · 纯 Rust 实现☆10Aug 7, 2026Updated 3 months ago
- ☆11Jul 11, 2024Updated 2 years ago
- ☆12Jan 5, 2026Updated 10 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) /…☆28Jul 7, 2026Updated 4 months ago
- MAZE (Massive Argumented Zonal Environments) machine learning framework☆11Mar 29, 2025Updated last year
- 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.
- ☆11Jul 10, 2026Updated 4 months ago
- An alternative implementation of auth microservice sample using Keycloak instead of Duende Identity Server☆11Sep 7, 2023Updated 3 years ago
- GLM-5.3-Flash EXL3 on 2x RTX PRO 6000☆23Updated this week
- Extract text data from documents using OCR (optical character recognition) technology and NER (named entity recognition).☆10May 11, 2023Updated 3 years ago
- ☆24Updated this week
- ☆13Jan 5, 2026Updated 10 months ago
- Tiny evaluation of leading LLMs on competitive programming problems☆15Apr 10, 2026Updated 7 months ago
Are these results useful?