Instructions to use majentik/gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use majentik/gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M 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 majentik/gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf majentik/gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf majentik/gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf majentik/gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M: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 majentik/gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf majentik/gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M: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 majentik/gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf majentik/gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M:Q4_K_M

Use Docker

docker model run hf.co/majentik/gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M:Q4_K_M

LM Studio
Jan

vLLM

How to use majentik/gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "majentik/gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "majentik/gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/majentik/gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M:Q4_K_M

Ollama
How to use majentik/gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M with Ollama:
```
ollama run hf.co/majentik/gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use majentik/gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M with Docker Model Runner:
```
docker model run hf.co/majentik/gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M:Q4_K_M
```

Lemonade

How to use majentik/gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull majentik/gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M:Q4_K_M

Run and chat with the model

lemonade run user.gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M-Q4_K_M

List all available models

lemonade list

Atomic Chat

majentik commited on May 6

Commit

90f7b21

verified ·

1 Parent(s): bec001f

docs: Tier 2 polish — variant matrix + quant trade-off

Browse files

Files changed (1) hide show

README.md +40 -0

README.md CHANGED Viewed

@@ -157,3 +157,43 @@ For VRAM-constrained setups, standard q8_0 KV cache quantization already halves
 - [TurboQuant paper (arXiv: 2504.19874)](https://arxiv.org/abs/2504.19874)
 - [Base model: google/gemma-4-31B-it](https://huggingface.co/google/gemma-4-31B-it)
 - [gemma-4-31B-it announcement](https://blog.google/technology/developers/gemma-4/)

 - [TurboQuant paper (arXiv: 2504.19874)](https://arxiv.org/abs/2504.19874)
 - [Base model: google/gemma-4-31B-it](https://huggingface.co/google/gemma-4-31B-it)
 - [gemma-4-31B-it announcement](https://blog.google/technology/developers/gemma-4/)
+## Quant trade-off (GGUF lane)
+| Quant | Approx size | Use case | Recommendation |
+|---|---|---|---|
+| Q2_K | ~17 GB | Lossy, low-RAM CPU/edge | Resource-constrained inference |
+| Q3_K_M | ~19 GB | Smaller-than-Q4, modest quality drop | Edge devices with ~16 GB RAM |
+| IQ4_XS | ~16 GB | Importance-quant 4-bit, smaller than Q4_K_M | Best size/quality at 4-bit |
+| **Q4_K_M** | ~23 GB | Balanced default | **Recommended for most users** |
+| Q5_K_M | ~24 GB | Higher fidelity than Q4 | Quality-sensitive applications |
+| Q6_K | ~28 GB | Approaching FP16 quality | High-fidelity CPU/edge |
+| Q8_0 | ~32 GB | Near-lossless reference | Fidelity-critical work |
+| MXFP4_MOE | ~17 GB | Microscaling FP4 (MoE-aware) | vLLM / transformers users |
+(Current variant — **Q4_K_M** — is bolded.)
+## Variants in this family
+(Showing 18 sibling variants under `majentik/gemma4-31b-it-*`. The current variant — `RotorQuant-GGUF-Q4_K_M` — is **bolded**.)
+| Variant | Runtime | Approx size | Use case |
+|---|---|---|---|
+| [RotorQuant](https://huggingface.co/majentik/gemma4-31b-it-rotorquant) | runtime modifier | n/a | KV-cache root (weight-agnostic) |
+| [RotorQuant-AWQ-4bit](https://huggingface.co/majentik/gemma4-31b-it-rotorquant-awq-4bit) | transformers | ~19 GB | GPU 4-bit (AutoAWQ) |
+| [RotorQuant-AWQ-8bit](https://huggingface.co/majentik/gemma4-31b-it-rotorquant-awq-8bit) | transformers | ~34 GB | GPU 8-bit (AutoAWQ) |
+| [RotorQuant-GGUF-IQ4_XS](https://huggingface.co/majentik/gemma4-31b-it-rotorquant-gguf-IQ4_XS) | llama.cpp | ~27 GB | Lossy 4-bit, low-RAM CPU/edge |
+| [RotorQuant-GGUF-Q2_K](https://huggingface.co/majentik/gemma4-31b-it-rotorquant-gguf-Q2_K) | llama.cpp | ~19 GB | Lossy, low-RAM CPU/edge |
+| [RotorQuant-GGUF-Q3_K_M](https://huggingface.co/majentik/gemma4-31b-it-rotorquant-gguf-Q3_K_M) | llama.cpp | ~24 GB | Smaller 3-bit, CPU-friendly |
+| **RotorQuant-GGUF-Q4_K_M** | llama.cpp | ~34 GB | Balanced default |
+| [RotorQuant-GGUF-Q5_K_M](https://huggingface.co/majentik/gemma4-31b-it-rotorquant-gguf-Q5_K_M) | llama.cpp | ~41 GB | Higher fidelity, more RAM |
+| [RotorQuant-GGUF-Q8_0](https://huggingface.co/majentik/gemma4-31b-it-rotorquant-gguf-Q8_0) | llama.cpp | ~65 GB | Near-lossless reference |
+| [RotorQuant-MLX-2bit](https://huggingface.co/majentik/gemma4-31b-it-rotorquant-mlx-2bit) | mlx-lm | ~9.9 GB | Apple Silicon, smallest |
+| [RotorQuant-MLX-4bit](https://huggingface.co/majentik/gemma4-31b-it-rotorquant-mlx-4bit) | mlx-lm | ~19 GB | Apple Silicon balanced |
+| [RotorQuant-MLX-8bit](https://huggingface.co/majentik/gemma4-31b-it-rotorquant-mlx-8bit) | mlx-lm | ~37 GB | Apple Silicon reference |
+| [TurboQuant](https://huggingface.co/majentik/gemma4-31b-it-turboquant) | runtime modifier | n/a | KV-cache root (weight-agnostic) |
+| [TurboQuant-AWQ-4bit](https://huggingface.co/majentik/gemma4-31b-it-turboquant-awq-4bit) | transformers | ~19 GB | GPU 4-bit (AutoAWQ) |
+| [TurboQuant-AWQ-8bit](https://huggingface.co/majentik/gemma4-31b-it-turboquant-awq-8bit) | transformers | ~34 GB | GPU 8-bit (AutoAWQ) |
+| [TurboQuant-MLX-2bit](https://huggingface.co/majentik/gemma4-31b-it-turboquant-mlx-2bit) | mlx-lm | ~9.9 GB | Apple Silicon, smallest |
+| [TurboQuant-MLX-4bit](https://huggingface.co/majentik/gemma4-31b-it-turboquant-mlx-4bit) | mlx-lm | ~19 GB | Apple Silicon balanced |
+| [TurboQuant-MLX-8bit](https://huggingface.co/majentik/gemma4-31b-it-turboquant-mlx-8bit) | mlx-lm | ~37 GB | Apple Silicon reference |