Instructions to use anilsuthar2004/qwen-bot 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 anilsuthar2004/qwen-bot 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 anilsuthar2004/qwen-bot # Run inference directly in the terminal: llama cli -hf anilsuthar2004/qwen-bot
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf anilsuthar2004/qwen-bot # Run inference directly in the terminal: llama cli -hf anilsuthar2004/qwen-bot
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf anilsuthar2004/qwen-bot # Run inference directly in the terminal: ./build/bin/llama cli -hf anilsuthar2004/qwen-bot
Use Docker
docker model run hf.co/anilsuthar2004/qwen-bot
- Llama new
- LM Studio
- Jan
- Ollama
How to use anilsuthar2004/qwen-bot with Ollama:
ollama run hf.co/anilsuthar2004/qwen-bot
- Unsloth Desktop
- Docker Model Runner
How to use anilsuthar2004/qwen-bot with Docker Model Runner:
docker model run hf.co/anilsuthar2004/qwen-bot
- Lemonade
How to use anilsuthar2004/qwen-bot with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull anilsuthar2004/qwen-bot
Run and chat with the model
lemonade run user.qwen-bot-{{QUANT_TAG}}List all available models
lemonade list
- Atomic Chat
Download llama.cpp/tools/ui/src/lib/utils/model-compatibility.ts from anilsuthar2004/qwen-bot: direct link, hf CLI and curl.
- Browser
- Download file 1.1 kB
-
https://huggingface.co/anilsuthar2004/qwen-bot/resolve/main/llama.cpp/tools/ui/src/lib/utils/model-compatibility.ts
- Command line
-
hf download hf://anilsuthar2004/qwen-bot/llama.cpp/tools/ui/src/lib/utils/model-compatibility.ts
-
curl -L -o model-compatibility.ts https://huggingface.co/anilsuthar2004/qwen-bot/resolve/main/llama.cpp/tools/ui/src/lib/utils/model-compatibility.ts
1.1 kB
| /** | |
| * Model memory estimation. | |
| * | |
| * Mirrors the app's compatibility check (Model+Compatibility.swift): the | |
| * runtime budget is RAM x 0.75 minus a fixed overhead, and a file fits when | |
| * its size with headroom stays under that budget. The result is the smallest | |
| * memory tier that can run the model, so the UI presents an honest machine | |
| * requirement instead of a raw file size. Context length and | |
| * device-specific budgets are deliberately ignored - callers present the | |
| * requirement and let the user judge. | |
| */ | |
| import { | |
| MB_PER_GB, | |
| MEM_TIERS, | |
| MIB_BYTES, | |
| QUANT_WEIGHT, | |
| RAM_BUDGET_RATIO, | |
| RAM_OVERHEAD_MB | |
| } from '$lib/constants'; | |
| /** | |
| * Smallest memory tier (GB) that can run a model of the given file size, | |
| * or null if nothing fits even the largest tier. | |
| */ | |
| export function minMemoryTierGb(sizeBytes: number): number | null { | |
| if (!sizeBytes) return null; | |
| const weightMb = (sizeBytes / MIB_BYTES) * QUANT_WEIGHT; | |
| for (const tier of MEM_TIERS) { | |
| const budgetMb = tier * MB_PER_GB * RAM_BUDGET_RATIO - RAM_OVERHEAD_MB; | |
| if (weightMb <= budgetMb) return tier; | |
| } | |
| return null; | |
| } | |