majentik/gemma-4-31B-TurboQuant-AWQ-8bit

Gemma 4 31B - TurboQuant AWQ 8-bit

8-bit AWQ-quantized version of google/gemma-4-31B (31B dense) with TurboQuant KV-cache quantization. AWQ (Activation-aware Weight Quantization) is an activation-aware method optimal for GPU inference. The 8-bit variant keeps quality very close to the FP16 baseline while halving VRAM usage.

Approximate model size: ~31 GB

Model Specifications

Property	Value
Base Model	google/gemma-4-31B
Parameters	~31 billion
Architecture	Dense transformer
Modality	Multimodal: image + text input, text output
License	Apache 2.0
Weight Quantization	AWQ 8-bit (~31 GB)
Group Size	128
KV-Cache Quantization	TurboQuant
Framework	transformers + AutoAWQ / vLLM

Quickstart

AutoAWQ

from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer

model = AutoAWQForCausalLM.from_quantized(
    "majentik/gemma-4-31B-TurboQuant-AWQ-8bit",
    device_map="auto",
    fuse_layers=True,
)
tokenizer = AutoTokenizer.from_pretrained("majentik/gemma-4-31B-TurboQuant-AWQ-8bit")

prompt = "The history of artificial intelligence began"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(out[0], skip_special_tokens=True))

vLLM

vllm serve majentik/gemma-4-31B-TurboQuant-AWQ-8bit \
  --quantization awq_marlin \
  --tensor-parallel-size 1 \
  --max-model-len 8192

What is TurboQuant?

TurboQuant (arXiv: 2504.19874) is a KV-cache quantization technique that compresses the key-value cache used during autoregressive generation. Combined with 8-bit AWQ weights, it delivers near-FP16 quality at roughly half the VRAM cost.

KV-Cache Quantization Comparison

Method	Prefill Speed	Decode Speed	Memory Savings	Reference
TurboQuant	1x (baseline)	1x (baseline)	High	arXiv: 2504.19874
RotorQuant	5.3x faster	28% faster	High	GitHub

AWQ vs GGUF vs MLX

Format	Target Hardware	Runtime	Best For
AWQ	NVIDIA / AMD GPU (CUDA/ROCm)	AutoAWQ, vLLM, TGI	GPU-native inference, production serving
GGUF	CPU + GPU (cross-platform)	llama.cpp, Ollama, LM Studio	Laptops, CPU-only boxes, mixed offload
MLX	Apple Silicon	MLX, mlx-lm, mlx-vlm	Macs with unified memory

This repo ships AWQ. See the "See Also" section for GGUF and MLX siblings.

Memory Estimates (Gemma 4 31B)

Precision	Approximate Size	VRAM Tier
FP16 (original)	~62 GB	80 GB+ (A100/H100)
AWQ 8-bit	~31 GB	40 GB+ (A100 40/80GB, L40S, 2x RTX 4090)
AWQ 4-bit	~17 GB	24 GB+

Best deployed on server-class GPUs (A100 40/80GB, L40S, H100) or dual RTX 4090 with tensor parallelism.

Hardware Requirements

• NVIDIA GPU with >=40 GB VRAM single-card, or 2x 24 GB cards with TP=2
• Recommended: A100 40GB, A100 80GB, L40S 48GB, H100 80GB
• CUDA 12.x recommended
• For vLLM: compute capability >= 7.5 (Turing or newer) for Marlin kernels

See Also

• google/gemma-4-31B -- Base model
• majentik/gemma-4-31B-TurboQuant -- TurboQuant KV-cache only (transformers)
• majentik/gemma-4-31B-TurboQuant-AWQ-4bit -- AWQ 4-bit variant
• majentik/gemma-4-31B-RotorQuant-AWQ-8bit -- RotorQuant AWQ 8-bit variant
• majentik/gemma-4-31B-TurboQuant-MLX-8bit -- MLX variant (Apple Silicon)
• TurboQuant Paper (arXiv: 2504.19874)
• AutoAWQ
• 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 — TurboQuant-AWQ-8bit — is bolded.)

Variant	Runtime	Approx size	Use case
RotorQuant	runtime modifier	n/a	KV-cache root (weight-agnostic)
RotorQuant-AWQ-4bit	transformers	~19 GB	GPU 4-bit (AutoAWQ)
RotorQuant-AWQ-8bit	transformers	~34 GB	GPU 8-bit (AutoAWQ)
RotorQuant-GGUF-IQ4_XS	llama.cpp	~27 GB	Lossy 4-bit, low-RAM CPU/edge
RotorQuant-GGUF-Q2_K	llama.cpp	~19 GB	Lossy, low-RAM CPU/edge
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	llama.cpp	~41 GB	Higher fidelity, more RAM
RotorQuant-GGUF-Q8_0	llama.cpp	~65 GB	Near-lossless reference
RotorQuant-MLX-2bit	mlx-lm	~9.9 GB	Apple Silicon, smallest
RotorQuant-MLX-4bit	mlx-lm	~19 GB	Apple Silicon balanced
RotorQuant-MLX-8bit	mlx-lm	~37 GB	Apple Silicon reference
TurboQuant	runtime modifier	n/a	KV-cache root (weight-agnostic)
TurboQuant-AWQ-4bit	transformers	~19 GB	GPU 4-bit (AutoAWQ)
TurboQuant-AWQ-8bit	transformers	~34 GB	GPU 8-bit (AutoAWQ)
TurboQuant-MLX-2bit	mlx-lm	~9.9 GB	Apple Silicon, smallest
TurboQuant-MLX-4bit	mlx-lm	~19 GB	Apple Silicon balanced
TurboQuant-MLX-8bit	mlx-lm	~37 GB	Apple Silicon reference