Category: Local LLM
GGUF Quantization Explained: Q4_K_M vs Q5_K_M vs Q8_0 and Which File to Download for Your VRAM
What every GGUF name means (Q4_K_M, IQ3_XS, Q8_0), how to calculate file size and VRAM including the KV cache, and which quant to pick for 8, 12, 16,…
Liquid AI LFM3: How to Run the 2B Text, Vision and Audio Models Locally (Ollama, llama.cpp, LM Studio)
LFM3 is Liquid AI’s new family of six open-weight 2B models. See the benchmarks, file sizes and exact Ollama, llama.cpp and LM Studio commands to run LFM3-1.7B, LFM3-VL-2B…
Nemotron 3.5 Bolt E4B 4GB: Which GGUF to Download, Real VRAM Use and RTX 5080 Speed Test
Nemotron 3.5 Bolt E4B 4GB on an RTX 5080: which GGUF to download, real VRAM use (3.5 GB at 8K), 145 tok/s in llama.cpp, and when DFlash helps.
Best Way to Run Recursive Flint Locally on a 16 GB GPU (NVFP4 + MoE Offload Guide)
Run Recursive Flint locally on a 16 GB GPU: the best quant for RTX 50-series (NVFP4), llama.cpp –n-cpu-moe offload math, context settings and agent setup.
How Much VRAM to Run Kimi K3 and K3.1 Pro? RAM, GPU and GGUF Table (2026)
Kimi K3.1 Pro is Moonshot’s 2.8T open-weight model that rivals Claude Opus 5.5. Specs, benchmarks, $2/$10 pricing, API example, the November open weights date and the real hardware…
How to Run MiniCPM-V 4.7 Locally: Ollama, llama.cpp and 16 GB GPU Settings
Run MiniCPM-V 4.7 (35B-A3B MoE and 1B) locally with Ollama, llama.cpp or vLLM: which GGUF quant fits your GPU, 16 GB tips, and OpenBMB’s recommended settings.
Mistral Large 4 Open Weights Are Out: License, File Sizes and Hardware to Run It
Mistral Large 4 open weights were released on October 29, 2026. The license terms, real FP8, NVFP4 and GGUF file sizes, and how to run the 1.05T MoE…
Can You Run Meta Muse Spark Open Locally? Hardware, Quants and Setup
Run Muse Spark Open locally: real RAM and VRAM needs for every quant, Mac Studio and server options, llama.cpp and Unsloth commands, benchmarks and license.