Gemma 4 E2B TurboQuant MLX 2bit

[!TIP] KV-cache quantization without any fork (recommended, 2026): upstream llama.cpp/Ollama now cover this natively — use -ctk q8_0 -ctv q8_0 (~half KV memory, negligible quality loss: perplexity +0.002–0.05) or -ctk q4_0 -ctv q4_0 (~quarter memory, ≈7.6% perplexity increase). In Ollama: OLLAMA_KV_CACHE_TYPE=q8_0 with OLLAMA_FLASH_ATTENTION=1. Keep K and V types symmetric to stay on the fast fused Flash-Attention path. Since April 2026, mainline llama.cpp also applies Hadamard rotation to KV activations (PR #21038), which greatly improves low-bit KV quality (opt-out: LLAMA_ATTN_ROT_DISABLE=1).

The RotorQuant/TurboQuant fork flow below is experimental/legacy: the TurboQuant llama.cpp PR was closed without merging (June 2026) and the fork is unmaintained relative to mainline. It is NOT required to use this model.

Gemma 4 E2B - TurboQuant MLX 2-bit

2-bit weight-quantized MLX version of google/gemma-4-E2B with TurboQuant KV-cache quantization. Optimized for Apple Silicon inference via the MLX framework. The most aggressive quantization, fitting the full model in the smallest possible footprint.

Approximate model size: ~0.6 GB

Model Specifications

Quickstart

import mlx.core as mx
from mlx_lm import load, generate

model, tokenizer = load("majentik/gemma-4-E2B-TurboQuant-MLX-2bit")

prompt = "The history of artificial intelligence began"
response = generate(model, tokenizer, prompt=prompt, max_tokens=512)
print(response)

For multimodal usage with images:

from mlx_vlm import load, generate

model, processor = load("majentik/gemma-4-E2B-TurboQuant-MLX-2bit")

prompt = "Describe the contents of this image."
output = generate(model, processor, prompt=prompt, image="path/to/image.jpg", max_tokens=512)
print(output)

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 2-bit weight quantization in MLX, this provides a dual compression strategy: smaller model weights for reduced disk and memory footprint, plus compressed KV cache for efficient long-context generation.

Note: 2-bit quantization is the most aggressive option and may result in some quality degradation compared to higher-precision variants. It is best suited for experimentation, rapid prototyping, or hardware-constrained environments.

KV-Cache Quantization Comparison

Memory Estimates (Gemma 4 E2B)

Hardware Requirements

This model requires approximately 0.6 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

• google/gemma-4-E2B -- Base model
• majentik/gemma-4-E2B-TurboQuant -- TurboQuant KV-cache only (transformers)
• majentik/gemma-4-E2B-TurboQuant-MLX-8bit -- MLX 8-bit variant
• majentik/gemma-4-E2B-TurboQuant-MLX-4bit -- MLX 4-bit variant
• majentik/gemma-4-E2B-RotorQuant-MLX-2bit -- RotorQuant MLX 2-bit variant
• TurboQuant Paper (arXiv: 2504.19874)
• MLX Framework

Quant trade-off (MLX lane)

(Current variant — 2bit — is bolded.)

Variants in this family

(Showing 14 sibling variants under majentik/gemma-4-e2b-*. The current variant — TurboQuant-MLX-2bit — is bolded.)