Instructions to use mudler/Gemopus-4-26B-A4B-it-Preview-APEX-GGUF 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 mudler/Gemopus-4-26B-A4B-it-Preview-APEX-GGUF 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 mudler/Gemopus-4-26B-A4B-it-Preview-APEX-GGUF:F16 # Run inference directly in the terminal: llama cli -hf mudler/Gemopus-4-26B-A4B-it-Preview-APEX-GGUF:F16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf mudler/Gemopus-4-26B-A4B-it-Preview-APEX-GGUF:F16 # Run inference directly in the terminal: llama cli -hf mudler/Gemopus-4-26B-A4B-it-Preview-APEX-GGUF:F16
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 mudler/Gemopus-4-26B-A4B-it-Preview-APEX-GGUF:F16 # Run inference directly in the terminal: ./llama-cli -hf mudler/Gemopus-4-26B-A4B-it-Preview-APEX-GGUF:F16
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 mudler/Gemopus-4-26B-A4B-it-Preview-APEX-GGUF:F16 # Run inference directly in the terminal: ./build/bin/llama-cli -hf mudler/Gemopus-4-26B-A4B-it-Preview-APEX-GGUF:F16
Use Docker
docker model run hf.co/mudler/Gemopus-4-26B-A4B-it-Preview-APEX-GGUF:F16
- LM Studio
- Jan
- Ollama
How to use mudler/Gemopus-4-26B-A4B-it-Preview-APEX-GGUF with Ollama:
ollama run hf.co/mudler/Gemopus-4-26B-A4B-it-Preview-APEX-GGUF:F16
- Unsloth Desktop
- Docker Model Runner
How to use mudler/Gemopus-4-26B-A4B-it-Preview-APEX-GGUF with Docker Model Runner:
docker model run hf.co/mudler/Gemopus-4-26B-A4B-it-Preview-APEX-GGUF:F16
- Lemonade
How to use mudler/Gemopus-4-26B-A4B-it-Preview-APEX-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull mudler/Gemopus-4-26B-A4B-it-Preview-APEX-GGUF:F16
Run and chat with the model
lemonade run user.Gemopus-4-26B-A4B-it-Preview-APEX-GGUF-F16
List all available models
lemonade list
- Atomic Chat
Banner: replace em dash with a comma
Browse files
README.md
CHANGED
|
@@ -17,13 +17,13 @@ tags:
|
|
| 17 |
<!-- apex-banner-v2 -->
|
| 18 |
<div style="background-color: #f59e0b; color: white; padding: 20px; border-radius: 10px; text-align: center; margin: 20px 0;">
|
| 19 |
<h2 style="color: white; margin: 0 0 10px 0;">β‘ Each donation = another big MoE quantized</h2>
|
| 20 |
-
<p style="font-size: 18px; margin: 0 0 15px 0;">I host <b>25+ free APEX MoE quantizations</b> as independent research. My only local hardware is an <b>NVIDIA DGX Spark</b> (122 GB unified memory)
|
| 21 |
<p style="font-size: 20px; margin: 0;">
|
| 22 |
<a href="https://www.patreon.com/cw/mudler" style="color: white; text-decoration: underline;">π Patreon (Monthly)</a> |
|
| 23 |
<a href="https://www.buymeacoffee.com/mudler" style="color: white; text-decoration: underline;">β Buy Me a Coffee</a> |
|
| 24 |
<a href="https://github.com/sponsors/mudler" style="color: white; text-decoration: underline;">β GitHub Sponsors</a>
|
| 25 |
</p>
|
| 26 |
-
<p style="font-size: 14px; margin: 10px 0 0 0; opacity: 0.9;">π Big thanks to Hugging Face for generously donating additional storage
|
| 27 |
</div>
|
| 28 |
|
| 29 |
# Gemopus 4 26B-A4B APEX GGUF
|
|
|
|
| 17 |
<!-- apex-banner-v2 -->
|
| 18 |
<div style="background-color: #f59e0b; color: white; padding: 20px; border-radius: 10px; text-align: center; margin: 20px 0;">
|
| 19 |
<h2 style="color: white; margin: 0 0 10px 0;">β‘ Each donation = another big MoE quantized</h2>
|
| 20 |
+
<p style="font-size: 18px; margin: 0 0 15px 0;">I host <b>25+ free APEX MoE quantizations</b> as independent research. My only local hardware is an <b>NVIDIA DGX Spark</b> (122 GB unified memory), enough for ~30-50B-class MoEs, but <b>bigger ones (200B+) require rented compute</b> on H100/H200/Blackwell, typically $20-100 per quant.<br>If APEX quants are useful to you, your support directly funds those bigger runs.</p>
|
| 21 |
<p style="font-size: 20px; margin: 0;">
|
| 22 |
<a href="https://www.patreon.com/cw/mudler" style="color: white; text-decoration: underline;">π Patreon (Monthly)</a> |
|
| 23 |
<a href="https://www.buymeacoffee.com/mudler" style="color: white; text-decoration: underline;">β Buy Me a Coffee</a> |
|
| 24 |
<a href="https://github.com/sponsors/mudler" style="color: white; text-decoration: underline;">β GitHub Sponsors</a>
|
| 25 |
</p>
|
| 26 |
+
<p style="font-size: 14px; margin: 10px 0 0 0; opacity: 0.9;">π Big thanks to Hugging Face for generously donating additional storage, much appreciated.</p>
|
| 27 |
</div>
|
| 28 |
|
| 29 |
# Gemopus 4 26B-A4B APEX GGUF
|