Instructions to use majentik/gemma-4-31B-RotorQuant-AWQ-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use majentik/gemma-4-31B-RotorQuant-AWQ-8bit with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="majentik/gemma-4-31B-RotorQuant-AWQ-8bit")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("majentik/gemma-4-31B-RotorQuant-AWQ-8bit", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use majentik/gemma-4-31B-RotorQuant-AWQ-8bit 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-RotorQuant-AWQ-8bit"
# 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-RotorQuant-AWQ-8bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/majentik/gemma-4-31B-RotorQuant-AWQ-8bit

SGLang

How to use majentik/gemma-4-31B-RotorQuant-AWQ-8bit with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "majentik/gemma-4-31B-RotorQuant-AWQ-8bit" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "majentik/gemma-4-31B-RotorQuant-AWQ-8bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "majentik/gemma-4-31B-RotorQuant-AWQ-8bit" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "majentik/gemma-4-31B-RotorQuant-AWQ-8bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use majentik/gemma-4-31B-RotorQuant-AWQ-8bit with Docker Model Runner:
```
docker model run hf.co/majentik/gemma-4-31B-RotorQuant-AWQ-8bit
```

majentik commited on 22 days ago

Commit

2ad41fd

verified ·

1 Parent(s): 78c063c

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

Browse files

Files changed (1) hide show

README.md +41 -9

README.md CHANGED Viewed

@@ -2,17 +2,15 @@
 license: apache-2.0
 base_model: google/gemma-4-31B
 tags:
-- awq
-- rotorquant
-- kv-cache-quantization
-- gemma
-- gemma4
-- quantized
-- 8bit
 library_name: transformers
 pipeline_tag: image-text-to-text
-language:
-- en
 ---
 # Gemma 4 31B - RotorQuant AWQ 8-bit
@@ -130,3 +128,37 @@ Best deployed on server-class GPUs (A100 40/80GB, L40S, H100) or dual RTX 4090 w
 - [llama-cpp-turboquant fork](https://github.com/johndpope/llama-cpp-turboquant/tree/feature/planarquant-kv-cache)
 - [AutoAWQ](https://github.com/casper-hansen/AutoAWQ)
 - [vLLM](https://github.com/vllm-project/vllm)

 license: apache-2.0
 base_model: google/gemma-4-31B
 tags:
+  - awq
+  - rotorquant
+  - kv-cache-quantization
+  - gemma
+  - gemma4
+  - quantized
+  - 8bit
 library_name: transformers
 pipeline_tag: image-text-to-text
 ---
 # Gemma 4 31B - RotorQuant AWQ 8-bit
 - [llama-cpp-turboquant fork](https://github.com/johndpope/llama-cpp-turboquant/tree/feature/planarquant-kv-cache)
 - [AutoAWQ](https://github.com/casper-hansen/AutoAWQ)
 - [vLLM](https://github.com/vllm-project/vllm)
+## Quant trade-off (AWQ lane)
+| Bits | Approx size | Use case | Recommendation |
+|---|---|---|---|
+| 4-bit | ~13 GB | Activation-aware 4-bit weight quant | GPU inference (vLLM, transformers, AutoAWQ) |
+| **8-bit** | ~24 GB | Activation-aware 8-bit weight quant | **Quality-sensitive GPU inference** |
+(Current variant — **8bit** — is bolded.)
+## Variants in this family
+(Showing 18 sibling variants under `majentik/gemma4-31b-*`. The current variant — `RotorQuant-AWQ-8bit` — is **bolded**.)
+| Variant | Runtime | Approx size | Use case |
+|---|---|---|---|
+| [RotorQuant](https://huggingface.co/majentik/gemma4-31b-rotorquant) | runtime modifier | n/a | KV-cache root (weight-agnostic) |
+| [RotorQuant-AWQ-4bit](https://huggingface.co/majentik/gemma4-31b-rotorquant-awq-4bit) | transformers | ~19 GB | GPU 4-bit (AutoAWQ) |
+| **RotorQuant-AWQ-8bit** | transformers | ~34 GB | GPU 8-bit (AutoAWQ) |
+| [RotorQuant-GGUF-IQ4_XS](https://huggingface.co/majentik/gemma4-31b-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-rotorquant-gguf-Q2_K) | llama.cpp | ~19 GB | Lossy, low-RAM CPU/edge |
+| [RotorQuant-GGUF-Q3_K_M](https://huggingface.co/majentik/gemma4-31b-rotorquant-gguf-Q3_K_M) | llama.cpp | ~24 GB | Smaller 3-bit, CPU-friendly |
+| [RotorQuant-GGUF-Q4_K_M](https://huggingface.co/majentik/gemma4-31b-rotorquant-gguf-Q4_K_M) | llama.cpp | ~34 GB | Balanced default |
+| [RotorQuant-GGUF-Q5_K_M](https://huggingface.co/majentik/gemma4-31b-rotorquant-gguf-Q5_K_M) | llama.cpp | ~41 GB | Higher fidelity, more RAM |
+| [RotorQuant-GGUF-Q8_0](https://huggingface.co/majentik/gemma4-31b-rotorquant-gguf-Q8_0) | llama.cpp | ~65 GB | Near-lossless reference |
+| [RotorQuant-MLX-2bit](https://huggingface.co/majentik/gemma4-31b-rotorquant-mlx-2bit) | mlx-lm | ~9.9 GB | Apple Silicon, smallest |
+| [RotorQuant-MLX-4bit](https://huggingface.co/majentik/gemma4-31b-rotorquant-mlx-4bit) | mlx-lm | ~19 GB | Apple Silicon balanced |
+| [RotorQuant-MLX-8bit](https://huggingface.co/majentik/gemma4-31b-rotorquant-mlx-8bit) | mlx-lm | ~37 GB | Apple Silicon reference |
+| [TurboQuant](https://huggingface.co/majentik/gemma4-31b-turboquant) | runtime modifier | n/a | KV-cache root (weight-agnostic) |
+| [TurboQuant-AWQ-4bit](https://huggingface.co/majentik/gemma4-31b-turboquant-awq-4bit) | transformers | ~19 GB | GPU 4-bit (AutoAWQ) |
+| [TurboQuant-AWQ-8bit](https://huggingface.co/majentik/gemma4-31b-turboquant-awq-8bit) | transformers | ~34 GB | GPU 8-bit (AutoAWQ) |
+| [TurboQuant-MLX-2bit](https://huggingface.co/majentik/gemma4-31b-turboquant-mlx-2bit) | mlx-lm | ~9.9 GB | Apple Silicon, smallest |
+| [TurboQuant-MLX-4bit](https://huggingface.co/majentik/gemma4-31b-turboquant-mlx-4bit) | mlx-lm | ~19 GB | Apple Silicon balanced |
+| [TurboQuant-MLX-8bit](https://huggingface.co/majentik/gemma4-31b-turboquant-mlx-8bit) | mlx-lm | ~37 GB | Apple Silicon reference |