llama.cpp fork for significantly improved performance on Ampere generation Nvidia cards (especially RTX 3090 / 3090 Ti): example: 110+ tok/s over a 100K-token generation at temperature 1 for qwen3.8, supporting full 262K ctx. Supports low memory (12gb) configs for 200k+ ctx. 120+ TPS, 3300+ prefill for QFN 3.8.
☆402Nov 19, 2026Updated this week
Alternatives and similar repositories for llamAmpere
Users that are interested in llamAmpere are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆134Updated 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 …☆2,751Nov 10, 2026Updated last week
- Hyper optimised Qwen3.8-27B inference on one RTX 3090: ReplaySSM, MTP3, reasoning effort, C1-C8 batching, and native Windows and Linux bu…☆523Oct 31, 2026Updated 2 weeks ago
- Pure-Rust inference engine for Qwen GGUF models (Qwen3 to Qwen3.8, dense and MoE up to 770B+). CUDA and Vulkan (NVIDIA, AMD), hybrid CPU+…☆291Updated this week
- Run Qwen3.8-27B at 140 tok/s on a single RTX 3090, up to 2x llama.cpp. Fast local LLM inference server with OpenAI- and Anthropic-compati…☆82Updated 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.
- Run GLM-5.3 (744B), GLM-5.3-Flash (321B), DeepSeek-V4.1-Flash (748B) and MiniMax-M3.1-Flash (428B) on your own GPUs - one engine, one das…☆3,061Updated this week
- Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, sglang, llama.cpp and other custom engines) and m…☆2,507Updated this week
- llama.cpp patch: faster MoE offload for models that don't fit in VRAM☆101Updated this week
- Qwen3.6 vLLM Toolkit — Launcher + Templates, Optimized for 2×24 GB. vLLM launcher with an optimized hybrid chat template drawing from the…☆13Aug 23, 2026Updated 2 months ago
- Qwen3.8-27B EXL3 (4.00 bpw) + DFlash2 speculative decoding for ExLlamaV3, validated at 262k context on a 24 GB RTX 3090☆25Sep 20, 2026Updated 2 months 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…☆107Nov 4, 2026Updated 2 weeks ago
- Fast open-source (MIT) LLM inference engine in C++/CUDA for RTX 3090-class GPUs: Qwen3.8-Flash-Next (~1,000 tok/s with 8 agents on 3x RTX…☆72Updated this week
- KVarN, KV cache precision tail, low-bit quants in llama.cpp for longer context of better precision in the same VRAM☆1,199Updated this week
- 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…☆110Nov 5, 2026Updated 2 weeks ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Qwen3.8-27B EXL3 + DFlash2 speculative decoding on an AMD RX 7900 XTX (exllamav3-rocm): recipe, patches, benchmarks☆23Nov 2, 2026Updated 2 weeks ago
- An easy to use TUI wizard for linux to extract maximum performance from your linux host and install Strata LLM☆81Updated this week
- Qwen3.8-Flash-Next at 262K context on an RTX 5090 + RTX 4070 Ti SUPER with 32 GB RAM: Strata patches (prefill on the big card, conversati…☆38Nov 11, 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…☆45,872Updated this week
- Your GeForce runs AI at half speed. This fixes it for 20/30/40 series cards. Up to 2× FP16 / BF16 / TF32 tensor throughput☆20,461Updated this week
- An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs☆1,840Updated this week
- Xolotl: run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 110 GB RAM): ~33 tok/s on agent tasks, ~4…☆542Updated 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 …☆1,163Updated this week
- LLM-powered research knowledge base — compile raw documents into a living wiki with persistent agent memory and RAG retrieval.☆14Apr 5, 2026Updated 7 months 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.
- 🚗 LIMCARS Local Inference Monitor · Cost Analyzer · Recipe Server☆13Nov 13, 2026Updated last week
- Fast Qwen3.8-27B for one RTX 3090. 200k context, 100+ tok/s. Custom CUDA decode engine, OpenAI-compatible API.☆42Updated this week
- Lucebox inference engine for heterogeneous hardware & consumer GPUs☆3,018Updated this week
- Fast local LLM inference on consumer GPUs: big Mixture-of-Experts models that don't fit in VRAM, OpenAI-compatible server, GGUF. A llama.…☆18Nov 12, 2026Updated last week
- C++/CUDA single-GPU inference engine for Qwen3.8 (incl. Qwen3.8-Flash-Next with offloaded experts) on the RTX 5090; grew from NInfer☆308Updated this week
- vLLM 0.33 fork for consumer GPUs: 3 x 262K sessions on Ampere,Ada and more! Qwen 3.8 Flash-Next at 207 tok/s, up to 17 on bigger cards. S…☆51Nov 12, 2026Updated last week
- Fastest validated sglang recipe for Qwen3.8-27B (AWQ-INT4 + DSpark) on RTX 3090s — 1×/2×/4× GPU presets, image+video, full benchmarks☆66Oct 17, 2026Updated last month
- 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…☆209Nov 8, 2026Updated last week
- Local inference engine optimized for NVIDIA Blackwell☆1,469Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- 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…☆252Updated this week
- High-performance single-GPU inference for selected model checkpoints and GPUs.☆3,387Updated this week
- An offline coding agent for local models. One command sets up the best model your GPU can run, and on 24 GB+ RTX 30/40/50-series cards Qw…☆147Updated this week
- Design 3D-printable parametric CAD models through conversational AI. Runs 100% locally with Ollama or cloud LLMs, featuring sandboxed Ope…☆16Nov 12, 2026Updated last week
- LLM inference in C/C++☆33Aug 1, 2026Updated 3 months ago
- LLM inference in C/C++☆55Updated this week
- Ethiopian Literature edited in TEI☆10Updated this week
Are these results useful?