Skip to content
localllm
日本語

shafire

Zero-Gemma4-E4B-OpenZero

Parameters
7.5B
Max context length
131,072
Architecture
gemma4
License
Commercial OK
Base model
unsloth/gemma-4-E4B-it
License
openzero-community-source-v1
llama.cpp
b8637+

About Zero-Gemma4-E4B-OpenZero

Zero-Gemma4-E4B-OpenZero is a GGUF model based on unsloth/gemma-4-E4B-it on Hugging Face. GGUF files are published by shafire/Zero-Gemma4-E4B-OpenZero-GGUF. It has about 7.5B parameters, the gemma4 architecture, a maximum context length of 131,072 tokens (values written in the GGUF).

There is one quantization, F16, with a file size of 5.87 GB (actual size on Hugging Face).

Running F16 (5.87 GB) with an 8,192-token context needs an estimated 7.12 GB of memory, and an estimated 7.52 GB at 32,768 tokens. For 8,192 tokens, a GPU with 8 GB or more of VRAM (such as GeForce RTX 3070 Ti, Arc A580), or a Mac with 8 GB or more of unified memory, is a rough guide (macOS caps how much memory the GPU can use, so leave some headroom).

The original model is licensed under Apache License 2.0, which allows commercial use (keep the license text and copyright notice when redistributing). Check the original license for the terms of use.

File size and estimated memory per quantization

  • Up to 8 GB
  • Up to 16 GB
  • Up to 24 GB
  • Up to 48 GB
  • Up to 128 GB
  • More

File sizes are the actual values on Hugging Face. Memory is estimated for each context length (KV cache f16). The formula is in How memory is calculated.

All memory figures are Estimated (KV cache f16). It should run on a setup with at least this much VRAM (or Mac unified memory). Click a value to see the devices and models that fit that amount (Find by GPU / Mac).

About the "quality guide" (how far a quantization drifts from the original)

For each quantization type, how far the output drifts from the original model, grouped into six levels from values llama.cpp measured on Llama-3-8B.

The value is mean KLD (the difference between the original and quantized model in next-token probabilities); smaller means closer to the original. Quantizations made with an imatrix (importance data) come out slightly smaller. Levels use the value without an imatrix (or with one, for types that only have that).

These values were not measured on this model. Larger models and MoE models tend to drift less with the same type. Distributor-specific mixed types (such as UD-Q4_K_XL) cannot be matched by type name alone, so they show "-".

Quantization Quality guide KLD (no imatrix) KLD (imatrix) Size (Llama-3-8B)
Q8_0 Nearly identical 0.0014 - 7.96 GiB
Q6_K Very small 0.0055 - 6.14 GiB
Q5_K_M Very small 0.0108 - 5.33 GiB
Q5_K_S Small 0.0166 - 5.21 GiB
Q5_1 Small 0.0180 - 5.65 GiB
Q5_0 Small 0.0222 - 5.21 GiB
Q4_K_M Small 0.0313 0.0282 4.58 GiB
Q4_K_S Medium 0.0431 0.0320 4.37 GiB
IQ4_NL Small - 0.0357 4.35 GiB
IQ4_XS Small - 0.0363 4.14 GiB
Q4_1 Medium 0.0717 - 4.78 GiB
Q4_0 Medium 0.0719 - 4.34 GiB
Q3_K_L Medium 0.0872 0.0731 4.03 GiB
Q3_K_M Medium 0.1019 0.0844 3.74 GiB
IQ3_M Medium - 0.1025 3.53 GiB
IQ3_S Medium - 0.1113 3.42 GiB
IQ3_XS Large - 0.1387 3.28 GiB
IQ3_XXS Large - 0.1836 3.05 GiB
Q3_K_S Large 0.2282 0.1998 3.41 GiB
IQ2_M Large - 0.3260 2.74 GiB
Q2_K Very large 0.4451 0.3322 2.96 GiB
Q2_K_S Very large - 0.4034 2.96 GiB
IQ2_S Very large - 0.4392 2.56 GiB
IQ2_XS Very large - 0.5463 2.43 GiB
IQ2_XXS Very large - 0.8120 2.24 GiB
IQ1_M Very large - 1.3931 2.01 GiB
IQ1_S Very large - 2.2546 1.88 GiB

Source: llama.cpp (MIT), measured on Llama-3-8B against FP16, Wikitext-2, revision f364eb6f. Original table · Reading and choosing quantizations

GGUF source

shafire/Zero-Gemma4-E4B-OpenZero-GGUF

Published by the original developer About this label

Last checked: Oct 14, 2026

Architecture
gemma4
llama.cpp b8637 and later
Parameters
7.5B
Max context length
131,072
License
apache-2.0 Commercial OK
File size and memory per quantization for Zero-Gemma4-E4B-OpenZero (shafire/Zero-Gemma4-E4B-OpenZero-GGUF)
Quantization File size Measured Quality guide 4,096 8,192 16,384 32,768 65,536 131,072 max
F16 5.87 GB Original precision 7.05 GB 7.12 GB 7.25 GB 7.52 GB 8.05 GB 9.13 GB 
Ollama  ollama run hf.co/shafire/Zero-Gemma4-E4B-OpenZero-GGUF:F16
llama.cpp  llama-server -hf shafire/Zero-Gemma4-E4B-OpenZero-GGUF:F16

Generation speed on common GPUs and Macs (estimated)

A rough guide to how fast F16 (5.87 GB) generates text. Each token reads the model weights once, so the upper limit is memory bandwidth ÷ file size. The guide is 60–80% of that, where most published measurements fall.

Device Memory bandwidth Guide (tokens/s) Estimated Upper limit
Arc A550M 8 GB 224 GB/s 23–31 38
Radeon RX 6800 16 GB 512 GB/s 52–70 87
GeForce RTX 5090 32 GB 1,792 GB/s 183–244 306
Apple M2 16 GB 100 GB/s 10–14 17
Apple M2 Pro 16 GB 200 GB/s 20–27 34
Apple M5 Ultra 96 GB 1,200 GB/s 123–164 205

Estimates only. Prompt processing speed (limited by compute) is not included. Longer contexts and offloading part of the model to the CPU make it slower. Macs are shown only when installed memory is at least 4/3 of what is needed. Devices without published bandwidth (some GeForce cards, etc.) are not shown.

License and commercial use

Apache License 2.0 Commercial OK

Allows commercial use, modification and redistribution. When redistributing, keep the license text and copyright notice, and note changes in modified files.

Based on the license on the original model's Hugging Face page. This differs from the GGUF repository's label (openzero-community-source-v1). Quantized files are made from the original model, so check the original model's license terms as well. Original license text (checked Oct 18, 2026)

The summary states facts this site read from the original text and is not legal advice. Always check the original license and its latest terms before use. All licenses

How to run

Mainline llama.cpp can load this model's format (gemma4) from b8637 (Apr 2, 2026) onward. Ollama and LM Studio bundle llama.cpp internally, so an older app fails to load it with errors such as "unknown model architecture". If that happens, update the app.

Example commands using F16. To use another quantization, replace the name with one from the table above. How to run local LLMs

Ollama

Run it by pointing directly at the GGUF on Hugging Face.

ollama run hf.co/shafire/Zero-Gemma4-E4B-OpenZero-GGUF:F16

llama.cpp

Pass the repository and quantization name to llama-server (or llama-cli) with -hf.

llama-server -hf shafire/Zero-Gemma4-E4B-OpenZero-GGUF:F16

LM Studio

Paste shafire/Zero-Gemma4-E4B-OpenZero-GGUF into the search box, download it, and choose the quantization from the file list.

Frequently asked questions

How much memory do I need to run Zero-Gemma4-E4B-OpenZero (F16)?
The file size is 5.87 GB (measured). With a 8,192-token context, the estimated memory including the KV cache is 7.12 GB. The formula is published at https://localllm.az-arte.com/en/guide/memory-calculation.
Can Zero-Gemma4-E4B-OpenZero be used commercially?
The original model's license is Apache License 2.0 (Commercial use allowed).Allows commercial use, modification and redistribution. When redistributing, keep the license text and copyright notice, and note changes in modified files. Check the original license text before deciding.
Does Zero-Gemma4-E4B-OpenZero run in 8 GB, 12 GB, 16 GB or 24 GB of VRAM?
8 GB: up to F16 (est. 7.12 GB); 12 GB: up to F16 (est. 7.12 GB); 16 GB: up to F16 (est. 7.12 GB); 24 GB: up to F16 (est. 7.12 GB) (estimated at 8,192 tokens with an f16 KV cache, files from the most-downloaded source).
What is the command to run Zero-Gemma4-E4B-OpenZero with Ollama?
Run "ollama run hf.co/shafire/Zero-Gemma4-E4B-OpenZero-GGUF:F16" to use the GGUF on Hugging Face directly. To use another quantization, replace the name at the end.