Package llama.cpp: Information

Plain C/C++ implementation (of inference of many LLM models) without
dependencies. AVX, AVX2, AVX512, and AMX support for x86 architectures.
Mixed F16/F32 precision. 1.5-bit, 2-bit, 3-bit, 4-bit, 5-bit, 6-bit, and
8-bit integer quantization for faster inference and reduced memory use.
Supports CPU, GPU, and hybrid CPU+GPU inference.

Supported models:

   LLaMA models, Mistral 7B, Mixtral MoE, Falcon, Chinese LLaMA /
   Alpaca and Chinese LLaMA-2 / Alpaca-2, Vigogne (French), Koala,
   Baichuan 1 & 2 + derivations, Aquila 1 & 2, Starcoder models, Refact,
   Persimmon 8B, MPT, Bloom, Yi models, StableLM models, Deepseek models,
   Qwen models, PLaMo-13B, Phi models, GPT-2, Orion 14B, InternLM2,
   CodeShell, Gemma, Mamba, Grok-1, Xverse, Command-R models, SEA-LION,
   GritLM-7B + GritLM-8x7B, OLMo, GPT-NeoX + Pythia,  Snowflake-Arctic
   MoE, Smaug, Poro 34B, Bitnet b1.58 models, Flan T5, Open Elm models,
   ChatGLM3-6b + ChatGLM4-9b + GLMEdge-1.5b + GLMEdge-4b, SmolLM,
   EXAONE-3.0-7.8B-Instruct, FalconMamba Models, Jais, Bielik-11B-v2.3,
   RWKV-6, QRWKV-6, GigaChat-20B-A3B, Trillion-7B-preview, Ling models,
   LFM2 models, Hunyuan models, BailingMoeV2 (Ring/Ling 2.0) models

Multimodal models:

   LLaVA 1.5 models, BakLLaVA, Obsidian, ShareGPT4V, MobileVLM 1.7B/3B
   models, Yi-VL, Mini CPM, Moondream, Bunny, GLM-EDGE, Qwen2-VL,
   LFM2-VL

NOTE:
  MODELS ARE NOT PROVIDED. You'll need to download them from the original
  sites (or Hugging Face Hub).

Overall this is all raw and EXPERIMENTAL, no warranty, no support.

Package llama.cpp: Information

Last changed