GLM-5.3-Flash EXL3 on one 24 GB RTX 3090 + DDR4: elastic GPU expert cache, zero-copy experts, AVX2 CPU tier, OpenAI API
☆313Oct 17, 2026Updated this week
Alternatives and similar repositories for glm-flash-lite
Users that are interested in glm-flash-lite are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Mirai S (Qwen3.8-27B-S trellis GGUF) on a 12 GB RTX 4070: 262k q8_0 tiered cache, MTP drafting at every depth, harness-proofing, the laye…☆93Updated this week
- LLM inference in C/C++☆56Aug 8, 2026Updated 2 months ago
- An AI assistant that lives in your browser. Built for collaboration, not autonomy theater. You guide, it executes. Automate repetitive we…☆98Sep 27, 2026Updated 2 weeks ago
- a node-based graphic design tool☆136Aug 7, 2026Updated 2 months ago
- One llama.cpp flag unlocks +33-39% decode speed for Qwen3.8-27B on consumer GPUs. The MTP head already ships inside your GGUF. Recipe, pa…☆363Sep 26, 2026Updated 3 weeks ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Heterogeneous prefill/decode for DeepSeek-V4-Flash: CUDA prefill (DGX Spark, vLLM) -> Metal decode (Mac Studio, oMLX) over plain 10GbE☆151Updated this week
- Grok Bot in the Omarchy bar☆46Sep 13, 2026Updated last month
- Project Maya - run GLM-5.3-Flash (321B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, s…☆999Updated this week
- A simple mono-repo build tool.☆66Updated this week
- Qwen3.8-27B on 16-32 GB Nvidia GPUs one-click install for Windows / Linux☆587Oct 9, 2026Updated last week
- run a 27b local ai on your gaming gpu, rtx 3060 and up, radeon rx 6600 and up in beta, 8gb or more, linux and windows, one line to instal…☆155Updated this week
- DeepSeek-V4.1-Flash on two DGX Sparks: EXL3 routed experts, 262k context, 2M-token KV, vision, tools, MTP, bundled with Pi☆91Oct 3, 2026Updated 2 weeks ago
- Qwen3.8-Flash-Next (125B MoE) on a 8GB+ Multi Vendor GPU 🥳No CUDA！☆204Updated this week
- LLM Inference Engine for Metal and CUDA.☆1,359Updated 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.
- JEPA-Anything: Learning Predictive Models across Different Worlds☆361Sep 18, 2026Updated 3 weeks ago
- Manage upto 1000 agents using automations and workflows☆38Updated this week
- Stop your coding agent from stalling real work on self-invented bookkeeping - receipts, hashes, locks, certification rituals. Ship first,…☆179Aug 31, 2026Updated last month
- ☆139Sep 30, 2026Updated 2 weeks ago
- Your AI intranet: network the computers you already own for inference and training.☆265Updated this week
- Universal utilities for working with graphs☆248Updated this week
- Faster inference backend for Open-Jev-27B: fused CUDA kernels, prefix tree, CUDA Graphs (B300, bf16)☆91Sep 28, 2026Updated 2 weeks ago
- 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 …☆2,040Updated this week
- All my walkthroughs for HTB Academy labs in the Active Directory Module ( CPTS path ). Includes folder of canvas files for Obsidian.☆67Apr 27, 2026Updated 5 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.
- qwen38-flash-next recipe for tp=2 GB10☆127Oct 6, 2026Updated last week
- Replacing lawyers with markdown files☆396Aug 12, 2026Updated 2 months ago
- NekoIMS is a portable IMS client built on top of BareSIP☆65Updated this week
- ☆41Aug 16, 2026Updated 2 months ago
- DeepSeek-V4.1-Flash EXL3 on one 24 GB RTX 3090 + DDR4 + NVMe: staged-DMA prefill, AVX2 CPU expert tier, elastic VRAM expert cache, Engram…☆143Updated this week
- lithos-metal: high-performance LLM inference kernels and serving for Apple silicon.☆272Updated this week
- Your iCloud Photos library as a native window on Omarchy. Sync with icloudpd, browse by day, delete with undo.☆52Updated this week
- MoJev: typed, calibrated decisions in one forward pass.☆29Sep 23, 2026Updated 3 weeks ago
- Reproduce Lium's LocalMaxxing leaderboard runs (7 boards, 20 Verified) on a rented Lium GPU in one script — vLLM/llama.cpp recipes, measu…☆36Sep 26, 2026Updated 3 weeks 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.
- Memecoin safety swarm on Solana: Instant Crawl scans, Launch Radar, Narrative Radar, Clean Launch on pump.fun, user-owned crawlers, x402 …☆103Updated this week
- Blob stream☆55Updated this week
- Refusal removal as a loadable KV-cache graft — zero weight modification, no refusal-direction projection, fully reversible.☆181Sep 21, 2026Updated 3 weeks ago
- Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on loca…☆26,707Updated this week
- llama.cpp fork for significantly improved performance on Ampere (especially RTX 3090 / 3090 Ti): example: 95+ tok/s over a 100K-token gen…☆178Updated this week
- Deep memory for agents over large datasets. Leviathan is a single static binary that turns your records (JSONL, JSON, CSV/TSV, SQLite, or…☆830Updated this week
- Code for free in claude-code, hermes, codex, vscode, .. and more☆69Sep 22, 2026Updated 3 weeks ago