Hackernews posts about Ollama Turbo

RSS feed for Ollama Turbo

01
newOllama Turboollama.com
▲ 430amram_art 458d 💬 243
02
newTq-KV – Rust implementation of TurboQuant that works on GGUF models
▲ 3onurgokyildiz 219d discuss
03
newShow HN: How to Use Google's Extreme AI Compression with Ollama and Llama.cpp
▲ 2anju-kushwaha 207d discuss
04
newLaunch HN: Magnitude (YC S25) – Self-optimizing inference engine for agentsgithub.com
▲ 194anerli 37d 💬 96
05
newShow HN: Open Access Qwen3.6-35B-A3B-UD-Q5_K_M with TurboQuant
▲ 4freakynit 203d 💬 2
06
newShow HN: Best setup local LLM found for a 5090 (llama.cpp fork + turboquant)local-llm.utop.workers.dev
▲ 2utopman 152d 💬 2
07
newThink Before You Speak – Exploratory Forced Hallucination Study [pdf]github.com
▲ 2airylizard 508d discuss
08
newQuantumLeap: 2.3× faster MoE inference with intelligent expert cachinggithub.com
▲ 1ikharoz 221d discuss
09
newShow HN: Qling – iOS podcast player with deep personalizationapps.apple.com
▲ 2bjar2 496d 💬 2
10
newFree AI API Key
▲ 5_ir0i 651d 💬 5
11
newTurboPrefill: 2.7× faster than llama.cpp Pipeline Parallel on Llama-3-70Bgithub.com
▲ 3trykhlieb 130d discuss
12
newShow HN: TurboPrefill – Multi-GPU prefill acceleration for llama.cppgithub.com
▲ 2trykhlieb 156d discuss
13
newTurboPrefill: 3.27× Prefill Speedup in Llama.cppdevpost.com
▲ 2trykhlieb 105d 💬 1
14
newShow HN: Run AI chat, image gen, vision, and voice offline on your Macgithub.com
▲ 11olie_h 130d 💬 4
15
newShow HN: I built a <400ms latency voice agent that runs on a 4gb vram GTX 1650"github.com
▲ 2shubham-coder 272d 💬 1
16
newShow HN: Open-source multimodal AI that runs in the browserjohnjboren.github.io
▲ 2EschatonCometh 302d 💬 1
17
newShow HN: Biscotti – on-device meeting transcription for macOS
▲ 1scosman 116d 💬 1
18
newComparing GenAI Inference Engines: TensorRT-LLM, VLLM, HF TGI, and LMDeploy
▲ 1juliensalinas 577d 💬 1
19
newTell HN: Avoid Cerebras if you are a founder
▲ 35remusomega 289d 💬 14