majentik/Nemotron-3-Nano-4B-RotorQuant-MLX-8bit

Nemotron-3-Nano-4B - RotorQuant MLX 8-bit

8-bit weight-quantized MLX version of nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16 with RotorQuant KV-cache quantization. Optimized for Apple Silicon inference via the MLX framework. RotorQuant delivers 5.3x faster prefill and 28% faster decode compared to TurboQuant. The dense hybrid Mamba-2 + Attention architecture supports up to 262K context length.

Approximate model size: ~4 GB

Model Specifications

Property	Value
Base Model	nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16
Parameters	4 billion (dense)
Architecture	Hybrid Mamba-2 + Attention (dense)
Context Length	262,144 tokens (262K)
License	NVIDIA Open Model License (commercial use OK)
Weight Quantization	8-bit (~4 GB)
KV-Cache Quantization	RotorQuant
Framework	MLX (Apple Silicon)

Quickstart

from mlx_lm import load, generate
from rotorquant import IsoQuantCache

model, tokenizer = load("majentik/Nemotron-3-Nano-4B-RotorQuant-MLX-8bit")

prompt = "Explain the theory of relativity."
response = generate(model, tokenizer, prompt=prompt, max_tokens=512)
print(response)

What is RotorQuant?

RotorQuant applies block-diagonal rotations (Clifford algebra) for KV cache compression. Combined with 8-bit weight quantization in MLX, this provides a dual compression strategy with superior KV-cache performance: smaller model weights plus faster compressed KV cache for efficient long-context generation.

Key advantages over TurboQuant:

• 5.3x faster prefill
• 28% faster decode
• Equivalent memory savings

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

Memory Estimates (Nemotron-3-Nano-4B)

Precision	Approximate Size	MLX Variant
BF16 (original)	~8 GB	--
8-bit quantized	~4 GB	This model
4-bit quantized	~2.3 GB	RotorQuant-MLX-4bit
2-bit quantized	~1.2 GB	RotorQuant-MLX-2bit

Hardware Requirements

This model requires approximately 4 GB of unified memory. Recommended hardware:

• Apple M1 (8 GB+)
• Apple M2 (8 GB+)
• Apple M3 (8 GB+)
• Apple M4 (8 GB+)
• Any Apple Silicon Mac with 8 GB+ unified memory

See Also

• nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16 -- Base model
• majentik/Nemotron-3-Nano-4B-RotorQuant -- RotorQuant KV-cache only (transformers)
• majentik/Nemotron-3-Nano-4B-RotorQuant-MLX-4bit -- MLX 4-bit variant
• majentik/Nemotron-3-Nano-4B-RotorQuant-MLX-2bit -- MLX 2-bit variant
• majentik/Nemotron-3-Nano-4B-TurboQuant-MLX-8bit -- TurboQuant MLX 8-bit variant
• RotorQuant GitHub
• MLX Framework

Quant trade-off (MLX lane)

Bits	Approx size	Use case	Recommendation
2-bit	~1.0 GB	Aggressive quantization	Very low-RAM Macs
3-bit	~1.4 GB	Lossy but small	Low-RAM Macs
4-bit	~1.7 GB	Balanced default	Recommended for most Macs
5-bit	~2.0 GB	Higher fidelity	Quality-sensitive
6-bit	~2.4 GB	Approaching FP16 quality	High-fidelity
8-bit	~3.0 GB	Near-lossless reference	Fidelity-critical work

(Current variant — 8bit — is bolded.)

Variants in this family

(Showing 13 sibling variants under majentik/nemotron3-nano-4b-*. The current variant — RotorQuant-MLX-8bit — is bolded.)

Variant	Runtime	Approx size	Use case
RotorQuant	runtime modifier	n/a	KV-cache root (weight-agnostic)
RotorQuant-GGUF-IQ4_XS	llama.cpp	~3.4 GB	Lossy 4-bit, low-RAM CPU/edge
RotorQuant-GGUF-Q2_K	llama.cpp	~2.4 GB	Lossy, low-RAM CPU/edge
RotorQuant-GGUF-Q3_K_M	llama.cpp	~3.1 GB	Smaller 3-bit, CPU-friendly
RotorQuant-GGUF-Q4_K_M	llama.cpp	~4.4 GB	Balanced default
RotorQuant-MLX-2bit	mlx-lm	~1.3 GB	Apple Silicon, smallest
RotorQuant-MLX-4bit	mlx-lm	~2.5 GB	Apple Silicon balanced
RotorQuant-MLX-8bit	mlx-lm	~4.7 GB	Apple Silicon reference
TurboQuant	runtime modifier	n/a	KV-cache root (weight-agnostic)
TurboQuant-GGUF-Q4_K_M	llama.cpp	~4.4 GB	Balanced default
TurboQuant-MLX-2bit	mlx-lm	~1.3 GB	Apple Silicon, smallest
TurboQuant-MLX-4bit	mlx-lm	~2.5 GB	Apple Silicon balanced
TurboQuant-MLX-8bit	mlx-lm	~4.7 GB	Apple Silicon reference