Qwen3.8-Flash-Next on 2× RTX 3090: with 128 GB RAM up to 4,191 tok/s prefill · 111.5 tok/s decode (131K prompt), full 256K window at 2,865 tok/s; with 64 GB RAM 3,410 tok/s prefill · 84 tok/s decode. New: opt-in uncensored mode (runtime abliteration, no new weights).
☆134Oct 15, 2026Updated 3 weeks ago
Alternatives and similar repositories for qwen38-flash-next-2x3090
Users that are interested in qwen38-flash-next-2x3090 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Unlock P2P comms between consumer NVIDIA GPUs☆697Oct 26, 2026Updated last week
- Single-file installer for a club-3090 webserver providing an admin control panel, a reverse proxy that automatically routes requests to t…☆28Jul 8, 2026Updated 3 months ago
- Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, sglang, llama.cpp and other custom engines) and m…☆2,477Updated this week
- Source-available C++/CUDA inference engine for Qwen3.8-27B INT4 on 3x RTX 3090☆41Updated this week
- Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when …☆2,580Updated this week
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Multi-GPU (tensor-parallel) CUDA megakernel for Qwen3.8-27B GGUF (Q4_K_M, Q5_K_M, Q6_K, Q8_0) with on-device MTP speculative decoding. Fo…☆16Oct 23, 2026Updated 2 weeks ago
- CLI port of BenchLocal quality bench packs — runs LLM behavioral evals against any OpenAI-compatible endpoint. Companion to club-3090.☆20Updated this week
- Run AMD AITER's hand-written ASM kernels on CDNA2 / gfx90a (MI210, MI250). 242 of 1,422 kernels translated, with the tests and benchmarks…☆11Sep 9, 2026Updated last month
- 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…☆22Updated this week
- What I run on my inference server: Qwen3.8-Flash-Next on two RTX 3090s, and how I got here☆17Oct 12, 2026Updated 3 weeks ago
- DeepSeek-V4.1-Flash-1017 (552B MoE + 196B Engram) on 2x RTX 3090 + 128 GB RAM. Rust + CUDA, T16 quantization. 40+ tok/s measured with exp…☆91Updated this week
- Native Vulkan inference for giant MoE models on consumer AMD GPUs☆18Sep 22, 2026Updated last month
- Optimized VLLM for Ampere☆25Oct 18, 2026Updated 2 weeks ago
- Qwen3.8-27B EXL3 + DFlash2 speculative decoding on an AMD RX 7900 XTX (exllamav3-rocm): recipe, patches, benchmarks☆21Updated this week
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Llama.cpp provider for GitHub Copilot on VS Code☆14May 23, 2026Updated 5 months ago
- Xolotl (formerly Strata-DSV4.1): run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 90 GB RAM) at up…☆467Updated this week
- ☆18Updated this week
- llama.cpp with Mirai S (2.4-bit Qwen3.8-27B) support: 128K context on a 12 GB GPU☆11Oct 7, 2026Updated 3 weeks ago
- Qwen and DeepSeek low-VRAM LoRA training with GGUF base model, compatible with Transformers and PEFT☆22Updated this week
- Real-world percentile benchmark for LLM inference servers: 1% A/B resolution, offline HTML reports. I am now on X also: https://x.com/bku…☆76Oct 9, 2026Updated 3 weeks ago
- Hyper optimised Qwen3.8-27B inference on one RTX 3090: ReplaySSM, MTP3, reasoning effort, C1-C8 batching, and native Windows and Linux bu…☆502Updated this week
- Development enviroment in docker.☆17Jun 21, 2016Updated 10 years ago
- Nearly empty starter repo for enterprise scale landing zones on Azure. Can be used with the bootstrap process (see README)☆13Feb 11, 2021Updated 5 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.
- Polyhedral Template Matching algorithm for analysis of molecular dynamics simulation data☆22Mar 22, 2020Updated 6 years ago
- OpenAI-compatible HTTP serving for diffusion language models. Continuous batching + LocalLeap acceleration.☆16May 26, 2026Updated 5 months ago
- Run GLM-5.3-Flash (321B), DeepSeek-V4.1-Flash (748B) and MiniMax-M3.1-Flash (428B) on your own GPUs - one engine, one dashboard, OpenAI- …☆2,585Updated this week
- 使用nvidia oam转接卡将intel gaudi2转接到pcie并在ubuntu下正常驱动和使用的指南☆29Updated this week
- vLLM fork for pascal gpu☆18Mar 13, 2026Updated 7 months ago
- A Federated Learning Method for Real-time Emotion State Classification from Multi-modal Streaming☆11Sep 15, 2022Updated 4 years ago
- The biggest arabic guide for hackintosh, now with support for opencore and macOS big sur☆11Feb 1, 2023Updated 3 years ago
- WebUI for managing llama-server sessions☆31Updated this week
- Single-request LLM serving recipes, patches, and benchmarks for modified RTX 2080 Ti 22GB / SM75 systems☆97Jun 10, 2026Updated 4 months 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.
- RHODS operator implementation, based on Kubeflow Operator☆14Updated this week
- Easy install Autodesk products on Fedora☆12Aug 18, 2020Updated 6 years ago
- 8mem core repo☆15Sep 29, 2026Updated last month
- GLM-5.3-Flash on 4× NVIDIA CMP 170HX with vLLM: up to 482.6 tok/s single-user, up to 943.7 tok/s at 8 users, 262K context, TP4 or PP4, on…☆88Oct 26, 2026Updated last week
- Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on loca…☆40,925Updated this week
- Docker Compose for llama.cpp GGUF servers on AMD Strix Halo: Qwen, Gemma, and Laguna packages (abliterated and quantized), stock Vulkan p…☆28Aug 17, 2026Updated 2 months ago
- llama.cpp fork for significantly improved performance on Ampere generation Nvidia cards (especially RTX 3090 / 3090 Ti): example: 110+ to…☆223Updated this week