Instructions to use Zrald/offline-ai-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Zrald/offline-ai-models with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf Zrald/offline-ai-models:Q4_K_M # Run inference directly in the terminal: llama cli -hf Zrald/offline-ai-models:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Zrald/offline-ai-models:Q4_K_M # Run inference directly in the terminal: llama cli -hf Zrald/offline-ai-models:Q4_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf Zrald/offline-ai-models:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Zrald/offline-ai-models:Q4_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf Zrald/offline-ai-models:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Zrald/offline-ai-models:Q4_K_M
Use Docker
docker model run hf.co/Zrald/offline-ai-models:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use Zrald/offline-ai-models with Ollama:
ollama run hf.co/Zrald/offline-ai-models:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use Zrald/offline-ai-models with Docker Model Runner:
docker model run hf.co/Zrald/offline-ai-models:Q4_K_M
- Lemonade
How to use Zrald/offline-ai-models with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Zrald/offline-ai-models:Q4_K_M
Run and chat with the model
lemonade run user.offline-ai-models-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Upload models/manifest.json with huggingface_hub
Browse files- models/manifest.json +46 -0
models/manifest.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": 4,
|
| 3 |
+
"updated": "2026-09-29",
|
| 4 |
+
"models": [
|
| 5 |
+
{
|
| 6 |
+
"id": "minicpm5-1b-q4k",
|
| 7 |
+
"name": "MiniCPM5-1B HyperQuant",
|
| 8 |
+
"file": "minicpm5-1b-q4k-v1.gguf",
|
| 9 |
+
"size": 566249056,
|
| 10 |
+
"sha256": "513ee6613a5b66ee8867ea14fcd46fc63c1a6744a42bd0ca82bacc06ee831ccf",
|
| 11 |
+
"ctx": 4096,
|
| 12 |
+
"threads": 6,
|
| 13 |
+
"quant": "Q4_K attn+ffn / Q2_K embed, imatrix",
|
| 14 |
+
"ppl_wikitext2": 29.118,
|
| 15 |
+
"baseline_ppl": 26.177
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"id": "falcon-ocr-q6k",
|
| 19 |
+
"name": "Falcon-OCR Q6_K",
|
| 20 |
+
"file": "falcon-ocr-q6_k.gguf",
|
| 21 |
+
"size": 223609696,
|
| 22 |
+
"sha256": "1c890c4eda058820e371d7bd876724d9b4df669ceaff707c2978a7562f6e20dc",
|
| 23 |
+
"ctx": 8192,
|
| 24 |
+
"threads": 4,
|
| 25 |
+
"quant": "Q6_K",
|
| 26 |
+
"type": "ocr",
|
| 27 |
+
"mmproj": "falcon-ocr-mmproj-f16.gguf",
|
| 28 |
+
"mmproj_size": 1199200,
|
| 29 |
+
"mmproj_sha256": "98179f4d62e5c0335c2ce189e57eb9f6c696ad7563850388238d4d348d450cf5"
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"id": "zrald-qwen38-27b-compressed",
|
| 33 |
+
"name": "Zrald Qwen3.8-27B (compressed)",
|
| 34 |
+
"file": "zraldqwen3.8-compressed.gguf",
|
| 35 |
+
"url": "https://huggingface.co/Zrald/Zrald-qwen3.8-27b-v2/resolve/main/zraldqwen3.8-compressed.gguf",
|
| 36 |
+
"size": 9828981664,
|
| 37 |
+
"sha256": "fd4730dd8aad070517978752b63d530aeb1740d2283cab9fa24f1e404032ddb0",
|
| 38 |
+
"ctx": 8192,
|
| 39 |
+
"threads": 6,
|
| 40 |
+
"quant": "Zrald compressed imatrix",
|
| 41 |
+
"min_ram_gb": 14,
|
| 42 |
+
"ppl_wikitext2": 0,
|
| 43 |
+
"baseline_ppl": 0
|
| 44 |
+
}
|
| 45 |
+
]
|
| 46 |
+
}
|