Local inference engine for Qwen3.8-Flash-Next on NVIDIA Blackwell
☆694Nov 6, 2026Updated this week
Alternatives and similar repositories for basalt
Users that are interested in basalt are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- C++/CUDA single-GPU inference engine for Qwen3.8 (incl. Qwen3.8-Flash-Next with offloaded experts) on the RTX 5090; grew from NInfer☆275Updated this week
- Strata fork: Qwen3.8-Flash-Next 125B MoE in NVFP4 on one RTX 20-50 card (12 GB+) and 64 GB of RAM or more. Setup installs our GPTQ quants…☆224Oct 24, 2026Updated last week
- The fastest inference engine for Qwen3.8-27B on the NVIDIA RTX 5090: up to 500 tokens/s for one agent and up to 2,000 tokens/s for many, …☆58Updated this week
- 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
- 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
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Qwen3.8-Flash-Next (MoE) and Qwen3.8-27B on one or two 16 GB RTX 50-series GPUs: experts offloaded to CPU, two-GPU tensor parallel. 64 GB…☆134Updated this week
- High-performance single-GPU inference for selected model checkpoints and GPUs.☆3,269Updated this week
- Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4 Flash, LFM2.5, Qwen3.6, Ornith …☆887Updated this 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
- ninfer-ext: Forked for speed.☆26Oct 22, 2026Updated 2 weeks ago
- LLM inference in C/C++☆471Updated this week
- LLM inference in C/C++☆39Updated 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
- OpenAI-compatible inference server for Qwen3.8 on one RTX 5090 / RTX PRO 6000: the 27B at ~170 tok/s (peaks ~370), Flash-Next (125B MoE) …☆54Updated this 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.
- An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs☆1,794Updated this week
- Pure-Rust MoE inference engine for Qwen3.5/3.6/3.8 GGUF. CPU+GPU hybrid experts, NVRTC CUDA kernels, OpenAI-compatible server. 2x llama.c…☆96Updated this week
- One line of NInfer for the Blackwell, Ada Lovelace, Ampere, Turing and Volta NVIDIA GPUs, consolidated from the forks that carry it: GGUF…☆196Updated this week
- Qwen3.8-Flash-Next at full 262k context on 8 GB RAM and 16 GB VRAM—20 tok/s generation and 1,600 tok/s prefill.☆63Oct 26, 2026Updated last week
- Qwen3.8-27B-GSQ3 on one RTX 4080: 100k context with rk4v4-e8, up to 2720 tok/s prefill and 262 tok/s generation☆34Oct 9, 2026Updated 3 weeks ago
- 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
- Native DeepSeek V4.1 Flash inference across one RTX PRO 6000 and four DGX Spark expert workers☆39Sep 25, 2026Updated last month
- Give GeForce cards (Turing and later) a BAR1 at least as large as their VRAM on Linux, without flashing.☆21Updated this week
- KVarN, KV cache precision tail, low-bit quants in llama.cpp for longer context of better precision in the same VRAM☆1,183Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- llama.cpp fork that abliterates at inference☆166Oct 24, 2026Updated 2 weeks ago
- Thinking blocks that open during generation: a gate decides when to think, a tree of candidate thoughts is explored, and the best one sta…☆18Oct 11, 2026Updated 3 weeks ago
- ☆37Oct 21, 2026Updated 2 weeks ago
- Berth is a lightweight GPU resource manager written in Go. It controls which applications get access to your GPU, when they get it, and h…☆288Updated this week
- SlopTV: an infinite AI slop generator from youtube comments☆42Aug 31, 2026Updated 2 months ago
- Stable, high-throughput inference server for multi-GPU NVIDIA V100 (SM70): Qwen3.8 Flash-Next with AWQ / NVFP4, multimodal input, CPU/dis…☆45Updated this week
- ☆50Updated this week
- Unlock P2P comms between consumer NVIDIA GPUs☆697Oct 26, 2026Updated last week
- Multi-dataset evaluation of Anthropic's J-Space on Qwen3-4B. Demonstrates that internal 'workspace noise' can reliably route high-confide…☆12Jul 13, 2026Updated 3 months ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- High-performance single-GPU inference for selected model checkpoints and GPUs.☆24Oct 13, 2026Updated 3 weeks ago
- More MoEs: a fork of Strata (Qwen3.8-Flash-Next, Qwen3.6/Ornith and more on one GPU + system RAM)☆25Updated this week
- Edit photos by describing the change, on your own GPU. A free, open-source alternative to Nano Banana and ChatGPT image editing: photos s…☆271Updated this week
- MRS-Core provides a transparent, modular, reproducible reasoning substrate.☆11Feb 3, 2026Updated 9 months ago
- A custom fork for frontier-scale mixture-of-experts inference on an RTX 3060 with 12 GB VRAM, 16 GB system RAM and local NVMe.** Betelge…☆95Updated this week
- An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, a…☆4,077Updated this week
- Strata minus the bullshit. clone, rsync to prod, compile and go☆219Updated this week