Qwen3.8-Flash-Next (W4A16) on 2x NVIDIA CMP 170HX with vLLM pipeline parallel: 226 tok/s single-user, 840 tok/s at 8 users, 262K context, HumanEval 157/164
☆12Nov 11, 2026Updated last week
Alternatives and similar repositories for cmp170hx-qwen38-flash-next
Users that are interested in cmp170hx-qwen38-flash-next are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- vLLM for NVIDIA CMP 170HX (Ampere sm_80): fast, repeatable model serving on one card or several☆31Nov 2, 2026Updated 2 weeks ago
- Tamper-evident audit trail for AI coding agent activity.☆17Jun 12, 2026Updated 5 months ago
- Known-good vLLM recipe: Qwen3.8-27B-Int8 + MTP speculative decoding on NVIDIA CMP 170HX 64GB (Hynix) — 84 tok/s, 262k ctx☆13Oct 8, 2026Updated last month
- NInfer SM80 port for NVIDIA CMP 170HX☆29Aug 22, 2026Updated 2 months ago
- Community-tested recipes, diagnostics, and benchmarks for CMP 170HX AI workloads☆101Nov 9, 2026Updated last week
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- defeating fuse security on ga100 with pico 2(and some wires)☆112Updated this week
- Local-first, LLM-agnostic memory system — hybrid retrieval (vector + lexical + graph), multi-signal ranking. Runs on 4GB RAM, CPU-only, n…☆17Oct 8, 2026Updated last month
- ComfyUI node for CLSS technology for MiniMax H3☆20Oct 1, 2026Updated last month
- Timestep-cache acceleration for MiniMax H3 in ComfyUI — open source, cross-platform, ~3x speedup measured☆19Aug 4, 2026Updated 3 months ago
- Qwen3.8-Flash-Next (W4A16) on 2x CMP 170HX: 110 tok/s decode, 7K prefill, 800 tok/s @ 23 concurrent - runs on 38 GB home RAM, no pinned m…☆20Sep 18, 2026Updated 2 months ago
- A cmpunlocker fork with working p2p on SYS-4028GR-TRT2☆27Aug 8, 2026Updated 3 months ago
- Expert Advisors and indicators for MetaTrader 5☆14Dec 28, 2025Updated 10 months ago
- MCP-сервер для КОМПАС-3D v24: ИИ-агент строит детали и сборки, а сервер проверяет каждый шаг измерением модели.☆18Updated this week
- Use this CDK stack to create a bastion host instance.☆17Sep 10, 2020Updated 6 years ago
- 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.
- Auto-built Docker image of 1Cat-vLLM for NVIDIA Tesla V100 (sm_70/Volta) with CUDA 12.8 — rebuilt daily when upstream releases☆13Jul 22, 2026Updated 3 months ago
- Adaptive Flutter widgets that resolve by platform, OS version and form factor — Liquid Glass on iOS 26 and macOS Tahoe, Material 3 Expres…☆11Sep 15, 2026Updated 2 months ago
- VFRAME Synthetic Image Training Data (early prototype, archived)☆12Nov 3, 2019Updated 7 years ago
- A planetary geared FDM filament extruder developed to work with the BLV Cube designed by Ben Levi. The design has two branches, one that…☆17Mar 7, 2021Updated 5 years ago
- unofficial version of eratoho TWKR☆25Aug 19, 2025Updated last year
- Run local LLMs on a Tesla V100-SXM2-16GB: prebuilt binaries, serve scripts, and setup for Windows and Linux (Qwen3 + Gemma 4, Claude Code…☆20Sep 1, 2026Updated 2 months ago
- ☆19Updated this week
- Fast vLLM on AMD Strix Halo: one docker command for Qwen, Gemma, LFM and more, up to 31x faster prefill and ~2x decode vs stock vLLM at l…☆22Nov 8, 2026Updated last week
- Exact LLM inference engine written from scratch for AMD Strix Halo (gfx1151, ROCm/HIP). Qwen3.8-Flash-Next on one node or two replicas; D…☆35Updated this week
- 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.
- 基于动态图数据库的动态超图知识检索系统,特性:五重检索内核(Vector语义、BM25关键词、Graph动态推理、上下文关联、实体多跳推理)、全属性实时演化、Agent语义重叠率智能自维护机制、轻量化超图架构。☆34Oct 10, 2025Updated last year
- ☆15Mar 15, 2026Updated 8 months ago
- ☆33Jul 25, 2026Updated 3 months ago
- ☆31Jun 15, 2025Updated last year
- Use the project to integrate LLM code review into your development and review processes.☆11Updated this week
- Android app that controls a Tasmota smart plug to limit battery charging without root.☆11Oct 22, 2025Updated last year
- NS AI Animata 是一款专为影视创作爱好者打造的 AI 驱动的小说转影视全流程工具,从小说文本到影视作品一站式生成,能力持续进化,既友好新手也支持深度自定义,与创作者同步成长。☆30May 13, 2026Updated 6 months ago
- Libegpu is a library for enumerating eGPU devices & enclosures.☆16Nov 24, 2025Updated 11 months ago
- ☆29Oct 1, 2023Updated 3 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.
- Official code of "Temporal Smoothness-Aware Rate-Distortion Optimized 4D Gaussian Splatting (NeurIPS 2025)"☆14Jan 6, 2026Updated 10 months ago
- GUI for LLaDA Diffusion LLM with Quantization for low end GPU and CPU options. Now with Prototype Training and Vector DB.☆12Mar 11, 2025Updated last year
- A deterministic inference engine for running large models on a single AMD Strix Halo 128 GB☆25Updated this week
- EdgeAI Kit — The missing UI toolkit for on-device LLMs in Flutter. Device checks, model management, recommendations, chat/vision/tool-cal…☆15May 5, 2026Updated 6 months ago
- MacOS on Lenovo ThinkPad X1 Tablet Gen3 Sequoia☆22Oct 18, 2026Updated last month
- ☆25Jun 27, 2026Updated 4 months ago
- Low-Latency Tensor Proxy☆21Oct 25, 2026Updated 3 weeks ago
Are these results useful?