Qwen3.8-27B on 2× RTX 5090 · 1.49M KV · code/prose t/s: c1 264/216, c16 2,649/2,240 · NVFP4 + vLLM + MTP
☆26Oct 21, 2026Updated 3 weeks ago
Alternatives and similar repositories for qwen3.8-27b-rtx5090
Users that are interested in qwen3.8-27b-rtx5090 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 (176B MoE) on a single RTX PRO 6000 Blackwell 96GB — NVMe-streamed PLE table, CUDA graphs with NEXTN speculation, meas…☆10Aug 28, 2026Updated 2 months ago
- Best-of-N coding agents with LLM-as-a-Verifier selection for Oh My Pi: isolated git worktrees, verifier-ranked trajectories, winner-only …☆77Nov 1, 2026Updated last week
- Qwen3.8-27B-NVFP4 on a Single RTX 5090 (vLLM)☆100Aug 16, 2026Updated 2 months ago
- Temperature-controlled 140 mm external fan for NVIDIA DGX Spark, using a Raspberry Pi Pico W.☆15Sep 13, 2026Updated last month
- A Homebridge plugin to control Levoit Core Air Purifiers with via the Vesync Platform.☆11Jul 6, 2021Updated 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.
- Optimized SGLang runtime for Qwen3.8-27B FP8 with DFlash2 and Qwen3.8 Flash-Next NVFP4 with FR-Spec on one NVIDIA RTX PRO 6000 Blackwell …☆195Updated this week
- UE5 Neurogame Template using Neurosity and experimental NodeJS plugin. See how the Javascript can be used to get information from your Ne…☆14Jul 31, 2023Updated 3 years ago
- Local-first, LLM-guided, coverage-driven fuzzer for network protocols and binary formats. Single Rust binary. Zero signup.☆15Jul 14, 2026Updated 3 months ago
- Validated vLLM recipe: Qwen3.8-27B-NVFP4 at full 262,144-token context on a single RTX 5090, GPU-only (no CPU offload).☆16Aug 20, 2026Updated 2 months ago
- Configuration files van automation using Home Assistant☆11Oct 16, 2024Updated 2 years ago
- Native DeepSeek V4.1 Flash inference across one RTX PRO 6000 and four DGX Spark expert workers☆41Sep 25, 2026Updated last month
- This repo helps to transform text into a better form for lora training☆12Apr 9, 2023Updated 3 years ago
- GLM-5.3-Flash EXL3 (320B MoE) on 2x NVIDIA DGX Spark — production serving kit, 1M context, 97%+ multi-session prefix caching, DFlash2 spe…☆65Nov 4, 2026Updated last week
- Generate and execute fuzzing campaign commands for AFL++ based on the recommended multi-core secondary fuzzer options.☆11Jan 12, 2024Updated 2 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Automates Flatcam generation of G-code for my (and maybe your) PCB milling process☆10Jun 16, 2023Updated 3 years ago
- A self-hosted control plane for a DGX Spark GPU cluster: provision nodes over SSH or a join token, deploy and serve inference behind one …☆13Oct 23, 2026Updated 2 weeks ago
- Kernel for the SDM845 modules☆18Updated this week
- ☆13Aug 1, 2024Updated 2 years ago
- Sharing benchmarks from DGX stations☆28Sep 11, 2026Updated 2 months ago
- Terminal system monitor (TUI) that builds its layout from the hardware it actually finds — hybrid CPU clusters, GPUs, RDMA/RoCE NICs, PCI…☆17Updated this week
- A bare minimum deployment of guardrails as a service.☆12Aug 13, 2026Updated 2 months ago
- A defensive decompilation layer: Ghidra facts, lifted into runnable Python & artifacts aiding analysis.☆16Aug 7, 2026Updated 3 months ago
- Output high level Pcode (PcodeAST) in Ghidra☆18Apr 7, 2023Updated 3 years ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- ☆12Aug 31, 2026Updated 2 months ago
- Universal ESP32 Diesel Hydronic/Heater controller☆17Oct 12, 2024Updated 2 years ago
- ☆12Apr 17, 2025Updated last year
- ☆11Dec 9, 2022Updated 3 years ago
- Experimental runtime reclamation of GB10 display-reserved memory into ordinary Linux RAM, with guarded driver, local signing, and reboot …☆13Oct 23, 2026Updated 2 weeks ago
- ☆13Sep 10, 2024Updated 2 years ago
- A studio rig for ComfyUI: one tabbed Workspace runs the whole image pipeline, from prompts and LoRAs to Paint with auto masks, Detailer, …☆16Oct 16, 2026Updated 3 weeks ago
- Docker that queries Starlinks Dishy and serves you the response on it's own web server☆12Nov 6, 2021Updated 5 years ago
- BTSync Ver.1.4.111, the last one with DHT.☆13Sep 3, 2019Updated 7 years 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.
- Pipecat Guess Who?☆16Aug 1, 2025Updated last year
- ☆12Sep 8, 2024Updated 2 years ago
- Claude Code skill: let your agent drive fleets of local omp (oh-my-pi) model instances toward one goal — provider config, bounded turns, …☆15Aug 28, 2026Updated 2 months ago
- Qwen3.8-27B on SGLang for NVIDIA RTX PRO 6000 (96GB, SM120): DSpark speculative decoding, full 256K context, 8 concurrent requests☆61Aug 24, 2026Updated 2 months ago
- First Int4-Int8Mix quantization of the full GLM-5.3 (743B), served on 4x NVIDIA DGX Spark (GB10) at TP4. Quantizer, verification gates, a…☆21Oct 6, 2026Updated last month
- Rest api server for Ecoflow devices☆14Jan 8, 2025Updated last year
- ☆18Dec 2, 2025Updated 11 months ago
Are these results useful?