Abliterated DeepSeek-V4.1-Flash-1017 (FP8 dense, FP4 experts) on 4x RTX PRO 6000 with vLLM-Moet r21, DSpark + FLy verification and top_p 1.0: 463 tok/s single-stream agent decode at 30k-120k context, 1082 tok/s over 8 streams, 1M context, Flex-start GCE VM
☆62Nov 12, 2026Updated last week
Alternatives and similar repositories for DeepSeek-V4.1-Flash-1017-FP8-abliterated-4x-RTX-PRO-6000
Users that are interested in DeepSeek-V4.1-Flash-1017-FP8-abliterated-4x-RTX-PRO-6000 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Recipe (profiles + docs) to serve Qwen3.8-Flash-Next on 1 or 2 DGX Sparks with the Zig TensorFold engine + Compute Lanes. Engine: github.…☆17Updated this week
- ☆16Oct 23, 2026Updated 3 weeks ago
- ☆31Apr 5, 2026Updated 7 months ago
- Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++☆21Updated this week
- Temperature-driven fan control for NVIDIA DGX Spark: full speed at ≥80 °C, back to EC auto at ≤70 °C. A bash script + systemd service bui…☆12Oct 13, 2026Updated last month
- 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.
- ⚡️Qwen-Image 4.8x🎉 speedup with Hybrid Acceleration for low VRAM GPUs☆17Oct 24, 2025Updated last year
- agentic cellular automata☆22Nov 5, 2026Updated 2 weeks ago
- Open WebUI tool to create, read, edit and export Excel (.xlsx) files preserving original styles. 7 functions: read, create, add rows, edi…☆12Sep 4, 2026Updated 2 months ago
- Self-hosted workspace sandboxes on GKE with gVisor and filesystem snapshots.☆76Updated this week
- A collection of custom tools and extensions for Open WebUI that enhance its capabilities☆13Dec 11, 2024Updated last year
- Everything your Hermes Bots and tools are waiting on you for, in one list: stuck sessions, failed crons, benched keys, PRs, and cards Bot…☆13Oct 23, 2026Updated 3 weeks ago
- A community-facing showcase: finished stacks, tools, functions, and pipes worth knowing about Open Webui☆17Nov 12, 2026Updated last week
- gobstopper is retired and no longer maintained. Source and historical artifacts remain available.☆14Nov 4, 2026Updated 2 weeks ago
- Retired. Excalibur (xcb) routed coding tasks across Codex and Claude Code subscriptions. Source and releases are preserved for reference.☆14Nov 2, 2026Updated 2 weeks ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Reproducible local multi-agent dev team: OpenRig + Claude Code + Codex + CLIProxyAPI + Jev. Plan in, user-tested features out.☆42Oct 5, 2026Updated last month
- ☆21Oct 17, 2025Updated last year
- ☆27Updated this week
- Agent skills from the Standard Agents team — install with npx skills add standardagents/skills@<skill>☆13Updated this week
- Breakable CUDA graph capture for PyTorch - capture compatible regions as CUDA graphs while running incompatible operations eagerly betwee…☆30Oct 8, 2026Updated last month
- A demonstrative example of running SGLang Diffusion with DP router☆26Mar 15, 2026Updated 8 months ago
- ALGAL is a programming language for agents. Programs pause for approvals, survive restarts, replay from recorded effects, and improve thr…☆20Nov 3, 2026Updated 2 weeks ago
- HarnessMM (arXiv 2610.32813) for pi: guarded decision reuse that runs a chain of dependent terminal steps inside one call instead of one …☆28Nov 2, 2026Updated 2 weeks ago
- fake CUTLASS to get peformance☆26Apr 28, 2026Updated 6 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.
- Reproducible Docker/vLLM deployment, tuning, and benchmarks for DeepSeek V4.1 Flash on a switchless three-node or four-node DGX Spark fab…☆235Updated this week
- Serve DeepSeek V4 Flash + DSpark on 4x RTX PRO 6000 (AWS g7e.24xlarge)☆29Aug 11, 2026Updated 3 months ago
- This is a source dump for our failed startup [Credport](http://www.credport.org).☆14Jun 6, 2014Updated 12 years ago
- YoungBar — a keyboard-first menu bar organizer for macOS 27.☆23Nov 11, 2026Updated last week
- NCU-driven iterative optimization workflow for CUDA/CUTLASS/Triton/CuTe DSL kernels.☆25Apr 10, 2026Updated 7 months ago
- Usual — your AI should know how you work. Local decision history for Claude Code and Codex. Started as Itchy; evolved through feedback.☆16Oct 26, 2026Updated 3 weeks ago
- Forking: Sudden Overfitting Under Replay - release code and project page☆11Oct 25, 2026Updated 3 weeks ago
- Narwhal is a keyword and KEY NARRATIVE manager that creates language-aware classes. Because Narhwal does not use NLP it avoids complexity…☆12Oct 16, 2018Updated 8 years ago
- vLLM inference solutions for NVIDIA GB10 (DGX Spark, sm121) — KIMI-K3 B12X_MLA + DSpark, GLM-5.2☆69Sep 30, 2026Updated last month
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- Clean reproducible benchmark suite for the self-hosted cascade RC (ARC-AGI-2, HMMT-2026, HLE, MMMU-Pro, SWE-Bench Pro, Terminal-Bench 2.1…☆13Nov 2, 2026Updated 2 weeks ago
- Python driver for MobilityDB☆12May 1, 2026Updated 6 months ago
- Applying the Chinese Wall Reverse Engineering Technique to Large Language Model Code Editing☆12Aug 2, 2025Updated last year
- DeepSeek V4.1 Flash on 4x RTX PRO 6000 Blackwell: native weights, DSpark, vision, NVMe or locked RAM Engram offload.☆92Oct 17, 2026Updated last month
- komo — comments for websites and agents☆17Oct 30, 2026Updated 2 weeks ago
- Autonomous GPU kernel optimization system driven by AI agents.☆32Mar 29, 2026Updated 7 months ago
- Open-source, self-hostable AI-native docs platform. Humans and AI agents as peer co-editors. Phase 1: architecture and ADRs.☆21Jul 2, 2026Updated 4 months ago
Are these results useful?