Instructions to use mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mradermacher/Llama-PLLuM-70B-chat-2412-i1-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 mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF: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 mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF: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 mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF with Ollama:
```
ollama run hf.co/mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF with Docker Model Runner:
```
docker model run hf.co/mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF:Q4_K_M
```

Lemonade

How to use mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Llama-PLLuM-70B-chat-2412-i1-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

mradermacher commited on May 23

Commit

bb95bda

verified ·

1 Parent(s): d7af619

auto-patch README.md

Browse files

Files changed (1) hide show

README.md +3 -0

README.md CHANGED Viewed

@@ -38,13 +38,16 @@ more details, including on how to concatenate multi-part files.
 | Link | Type | Size/GB | Notes |
 |:-----|:-----|--------:|:------|
 | [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-70B-chat-2412.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) |
 | [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-70B-chat-2412.i1-IQ2_M.gguf) | i1-IQ2_M | 24.2 |  |
 | [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-70B-chat-2412.i1-Q2_K.gguf) | i1-Q2_K | 26.5 | IQ3_XXS probably better |
 | [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-70B-chat-2412.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 27.6 | lower quality |
 | [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-70B-chat-2412.i1-IQ3_M.gguf) | i1-IQ3_M | 32.0 |  |
 | [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-70B-chat-2412.i1-Q3_K_M.gguf) | i1-Q3_K_M | 34.4 | IQ3_S probably better |
 | [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-70B-chat-2412.i1-Q4_K_S.gguf) | i1-Q4_K_S | 40.4 | optimal size/speed/quality |
 | [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-70B-chat-2412.i1-Q4_K_M.gguf) | i1-Q4_K_M | 42.6 | fast, recommended |
 Here is a handy graph by ikawrakow comparing some lower-quality quant
 types (lower is better):

 | Link | Type | Size/GB | Notes |
 |:-----|:-----|--------:|:------|
 | [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-70B-chat-2412.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) |
+| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-70B-chat-2412.i1-IQ1_M.gguf) | i1-IQ1_M | 16.9 | mostly desperate |
 | [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-70B-chat-2412.i1-IQ2_M.gguf) | i1-IQ2_M | 24.2 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-70B-chat-2412.i1-Q2_K_S.gguf) | i1-Q2_K_S | 24.6 | very low quality |
 | [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-70B-chat-2412.i1-Q2_K.gguf) | i1-Q2_K | 26.5 | IQ3_XXS probably better |
 | [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-70B-chat-2412.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 27.6 | lower quality |
 | [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-70B-chat-2412.i1-IQ3_M.gguf) | i1-IQ3_M | 32.0 |  |
 | [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-70B-chat-2412.i1-Q3_K_M.gguf) | i1-Q3_K_M | 34.4 | IQ3_S probably better |
 | [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-70B-chat-2412.i1-Q4_K_S.gguf) | i1-Q4_K_S | 40.4 | optimal size/speed/quality |
 | [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-70B-chat-2412.i1-Q4_K_M.gguf) | i1-Q4_K_M | 42.6 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-70B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-70B-chat-2412.i1-Q6_K.gguf) | i1-Q6_K | 58.0 | practically like static Q6_K |
 Here is a handy graph by ikawrakow comparing some lower-quality quant
 types (lower is better):