Qwen3.8-27B INT8 + DFlash2 on a rented CMP 170HX — failure analysis (private GHCR image prevented benchmark)
☆17Aug 30, 2026Updated 2 months ago
Alternatives and similar repositories for Qwen3.8-27B-CMP-170HX
Users that are interested in Qwen3.8-27B-CMP-170HX are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 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 last month
- NInfer SM80 port for NVIDIA CMP 170HX☆29Aug 22, 2026Updated 2 months ago
- Async PLE SSD offload for Qwen3.8 Flash Next on a 64 GiB SM80 GPU: vLLM patch, setup guide, and measured PP/TG results.☆23Sep 24, 2026Updated last month
- dsv41-flash-pp5-170hx &pp6 Supports the original (full/unquantized) model. Prefill 7,000 t/s, decode 45-75-125 t/s. dspark. Requires 200 …☆13Nov 2, 2026Updated last week
- Community-tested recipes, diagnostics, and benchmarks for CMP 170HX AI workloads☆98Updated this week
- 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.
- DeepSeek-V4.1-Flash on 4× NVIDIA CMP 170HX with vLLM: up to 297 tok/s for one user, up to 868 tok/s at eight, 262K context, one-command c…☆25Nov 2, 2026Updated last week
- A tool to unlobotomize your NVIDIA card!☆837Oct 28, 2026Updated 2 weeks ago
- The original as far as I could find.☆14Feb 10, 2025Updated last year
- 限制问题区域显存 62906MiB / 65024MiB 支持驱动 610.57.04 ，修改显卡显示名称为NVIDIA Tesla A100☆13Aug 30, 2026Updated 2 months ago
- DeepSeek-V4-Flash-0731 on 4x CMP 170HX (sm_80): 98 tok/s decode, ~5300 tok/s prefill. DSpark speculative decoding under pipeline parallel…☆118Aug 13, 2026Updated 2 months ago
- 在四卡A100上适配Sglang部署deepseek-v4-flash正式版模型☆14Aug 2, 2026Updated 3 months ago
- 将简单设定扩写成中国式宏大场景故事、连续分镜与成对图片视频提示词的 Codex Skill☆13Aug 18, 2026Updated 2 months ago
- ☆11Oct 18, 2026Updated 3 weeks ago
- Active4j-jsp是基于SpingBoot2.0轻量级的java快速开发框架。以Spring Framework为核心容器，Spring MVC为模型视图控制器，Mybatis Plus为数据访问层， Apache Shiro为权限授权层, Redis为分布式缓存，Q…☆15Feb 11, 2026Updated 9 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- A laptop keyboard reverse-engineering helper☆14Jun 12, 2022Updated 4 years ago
- vLLM 0.33 fork for consumer GPUs: 3 x 262K sessions on 4x RTX 3090, Qwen 3.8 Flash-Next at 207 tok/s, up to 17 on bigger cards. Seven che…☆48Updated this week
- Kotai is a fully local, zero-cost voice assistant that combines the power of Kyutai TTS/STT, LiveKit, and local LLMs to create natural co…☆10Jul 14, 2025Updated last year
- ☆15Aug 23, 2026Updated 2 months ago
- vLLM for NVIDIA CMP 170HX (Ampere sm_80): fast, repeatable model serving on one card or several☆27Nov 2, 2026Updated last week
- Android chroot guide + other useful scripts☆13Jul 28, 2025Updated last year
- DeepSeek-V4.1-Flash (764B) on 4×CMP 170HX: PP4 + shadow KV + EXL3 2bpw + DSpark + 512k ctx + native vision — patches, recipes, acceptance…☆15Sep 29, 2026Updated last month
- Standalone CLI tool to find company CEO names using SearXNG web search and LLM analysis (Gemini, OpenAI, Groq, Ollama).☆14Apr 25, 2025Updated last year
- glm-5.2 on too many 64 / 80 GB A100's☆22Sep 9, 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.
- Updated voice agent with Nemotron 3.5 ASR☆19Jun 4, 2026Updated 5 months ago
- Web and MacOS App to scrape data from Google Maps. Extracts data such as the name, address, phone number, website URL, rating, reviews n…☆16Jun 13, 2025Updated last year
- Script to fetch a copy of the Gadgetbridge database and extract data for Huami devices for writing onwards into InfluxDB☆18Jan 24, 2026Updated 9 months ago
- ☆21Jan 31, 2025Updated last year
- 🤖 Discover free API access and credits for various legitimate large language model services in one curated resource list.☆34Oct 12, 2026Updated 3 weeks ago
- ☆33Jul 25, 2026Updated 3 months ago
- OpenCore EFI for X79 Mainboard and CPU xeon E5 2650v2 RX470☆20Feb 1, 2021Updated 5 years ago
- Booking model context protocol server☆16Oct 27, 2025Updated last year
- TR069 based Auto Configuration Server (ACS) using CWMP☆17Feb 21, 2016Updated 10 years 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.
- Robin LLM is a Java-based service that crawls OpenRouter's website for free LLM models, continuously tests their performance, and provide…☆24May 17, 2026Updated 5 months ago
- Frontend program for gogcli.exe by Magnitus☆22Oct 11, 2026Updated last month
- Train Llama Loras Easily☆30Aug 3, 2023Updated 3 years ago
- Notre expérience avec le service SGE Tiers d‘Enedis☆19Sep 14, 2023Updated 3 years ago
- A Docker-based OpenAI-compatible Text-to-Speech API server powered by Kyutai's TTS models with GPU acceleration support.☆22Jul 12, 2025Updated last year
- Some Steam patches, fixing broken Steam features on Asus Rog Ally☆35Dec 10, 2024Updated last year
- 解锁自有 NVIDIA CMP 170HX / 90HX 的算力限制。Linux x86-64，需要 root。☆62Aug 6, 2026Updated 3 months ago
Are these results useful?