Skip to content
Local AI Wizard
Your machine
Theme

Gemma 4 E4B

Google · google/gemma-4-E4B-it

Text & chatVisionAudioVideo

Q4 file 5.0 GB (Q4_K_M) · runs well from 12 GB · Weights license: Apache 2.0

Reported by the publisher15 resultsGoogle's model card · read 2026-10-25 · not ranked · see them
Memory needed~6 GBQ4 weights + working room, before the machine's reserve
Parameters8 Bmanufacturer specification
Context131,072 tokensPublished for this model

Quality

No result in LiveBench 2026-06-25, LMArena 2026-10-22 Not in LiveBench 2026-06-25 or LMArena 2026-10-22

Reported by the publisher

15 results · Google's model card · read 2026-10-25
MMLU Pro
69.4%
AIME 2026 no tools
42.5%
LiveCodeBench v6
52.0%
Codeforces ELO
940
GPQA Diamond
58.6%
Tau2 (average over 3)
42.2%
BigBench Extra Hard
33.1%
MMMLU
76.6%
Every reported result15
MMMU Pro
52.6%Vision
OmniDocBench 1.5 (average edit distance, lower is better)
0.181Vision
MATH-Vision
59.5%Vision
MedXPertQA MM
28.7%Vision
CoVoST
35.54Audio
FLEURS (lower is better)
0.08Audio
MRCR v2 8 needle 128k (average)
25.4%Long Context
Across Gemma 4 sizes15 shared results · same publisher and settings
Gemma 4: results the publisher reports for each size under the same settings
Benchmark (publisher settings)E2BE4B12B26B A4B31B
MMLU Pro60.0%69.4%77.2%82.6%85.2%
AIME 2026 no tools37.5%42.5%77.5%88.3%89.2%
LiveCodeBench v644.0%52.0%72.0%77.1%80.0%
Codeforces ELO6339401,6591,7182,150
GPQA Diamond43.4%58.6%78.8%82.3%84.3%
Tau2 (average over 3)24.5%42.2%69.0%68.2%76.9%
BigBench Extra Hard21.9%33.1%53.0%64.8%74.4%
MMMLU67.4%76.6%83.4%86.3%88.4%
MMMU Pro · Vision44.2%52.6%69.1%73.8%76.9%
OmniDocBench 1.5 (average edit distance, lower is better) · Vision0.2900.1810.1640.1490.131
MATH-Vision · Vision52.4%59.5%79.7%82.4%85.6%
MedXPertQA MM · Vision23.5%28.7%48.7%58.1%61.3%
CoVoST · Audio33.4735.5438.5This size's card does not report this result under these settingsThis size's card does not report this result under these settings
FLEURS (lower is better) · Audio0.090.080.069This size's card does not report this result under these settingsThis size's card does not report this result under these settings
MRCR v2 8 needle 128k (average) · Long Context19.1%25.4%43.4%44.1%66.4%

Values as printed on the card, with the publisher's own settings (card section: Benchmark Results); column “Gemma 4 E4B”. Not comparable across publishers and not used in any ranking. Model card

Run it

Run it

File Q4_K_M · 5 GB · unsloth/gemma-4-E4B-it-GGUF · What is Q4?

ollama run hf.co/unsloth/gemma-4-E4B-it-GGUF:Q4_K_M
  1. Install Ollama
  2. Run the command above
  3. Ask: Explain what a context window is, in two sentences.

Runs on

Fast memory holds it 114

The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.

Show all 114

Within memory, outside the fast part 5

Within the machine's memory, outside its fast part: on a graphics card the layers that do not fit run on the CPU from PC RAM (the listed RAM, or 32 GB assumed); on a Mac, above the macOS default GPU share. Not a speed figure.

Show all 5

Gemma 4 E4B is a text model from Google with 8B parameters. It was released on March 31, 2026 and reads up to 131,072 tokens of context. Its Q4 weights plus working room come to about 6 GB before the machine's reserve; the smallest reference machines whose fast memory holds that are Mac mini M2 · 8 GB unified (~8 GB with its reserve) and RTX 4060 · 8 GB VRAM (~8 GB with its reserve). We collected 24 downloadable GGUF and MLX files from 2 publisher sources; the most downloaded GGUF source is unsloth's. It has no result in LiveBench 2026-06-25, so no quality score is shown.

Hardware profiles grouped by the Q4 planning estimate on each machine (dedicated GPUs reserve 2 GB; unified and system memory 25%, 2 to 8 GB): the fast memory holds it, it is within memory but outside the fast part (layers offloaded to PC RAM, or above the macOS GPU share), or the machine is one memory tier short. Each card opens its hardware profile. Not a measured fit or speed.

On the reference machines

Gemma 4 E4B on the reference machines
Where Q4 sits
Mac mini M2 · 8 GB unifiedFast memory holds itIQ4_XSGGUF · 4.7 GB · needs ~8 GB16,384 tokens~8 GBFast memory holds itIQ4_XSGGUF · 4.7 GB · needs ~8 GB16,384 tokens
Mac mini M4 · 16 GB unifiedFast memory holds itQ8_0GGUF · 8.2 GB · needs ~14 GB131,072 tokens~10 GBFast memory holds itQ8_0GGUF · 8.2 GB · needs ~14 GB131,072 tokens
Mac mini M4 · 24 GB unifiedFast memory holds itQ8_0GGUF · 8.2 GB · needs ~16 GB131,072 tokens~12 GBFast memory holds itQ8_0GGUF · 8.2 GB · needs ~16 GB131,072 tokens
Mac mini M4 · 32 GB unifiedFast memory holds itQ8_0GGUF · 8.2 GB · needs ~18 GB131,072 tokens~14 GBFast memory holds itQ8_0GGUF · 8.2 GB · needs ~18 GB131,072 tokens
Mac mini M5 Pro · 64 GB unifiedFast memory holds itQ8_0GGUF · 8.2 GB · needs ~18 GB131,072 tokens~14 GBFast memory holds itQ8_0GGUF · 8.2 GB · needs ~18 GB131,072 tokens
Mac Studio M5 Max · 128 GB unifiedFast memory holds itQ8_0GGUF · 8.2 GB · needs ~18 GB131,072 tokens~14 GBFast memory holds itQ8_0GGUF · 8.2 GB · needs ~18 GB131,072 tokens
Mac Studio · M5 Ultra · 36-core CPU / 80-core GPU · 512 GB unifiedFast memory holds itQ8_0GGUF · 8.2 GB · needs ~18 GB131,072 tokens~14 GBFast memory holds itQ8_0GGUF · 8.2 GB · needs ~18 GB131,072 tokens
RTX 4060 · 8 GB VRAMFast memory holds itIQ4_XSGGUF · 4.7 GB · needs ~8 GB16,384 tokens~8 GBFast memory holds itIQ4_XSGGUF · 4.7 GB · needs ~8 GB16,384 tokens
RTX 3060 · 12 GB VRAMFast memory holds itQ8_0GGUF · 8.2 GB · needs ~12 GB8,192 tokens~8 GBFast memory holds itQ8_0GGUF · 8.2 GB · needs ~12 GB8,192 tokens
RTX 5080 · 16 GB VRAMFast memory holds itQ8_0GGUF · 8.2 GB · needs ~12 GB131,072 tokens~8 GBFast memory holds itQ8_0GGUF · 8.2 GB · needs ~12 GB131,072 tokens
RTX 4090 · 24 GB VRAMFast memory holds itQ8_0GGUF · 8.2 GB · needs ~12 GB131,072 tokens~8 GBFast memory holds itQ8_0GGUF · 8.2 GB · needs ~12 GB131,072 tokens
RTX 5090 · 32 GB VRAMFast memory holds itQ8_0GGUF · 8.2 GB · needs ~12 GB131,072 tokens~8 GBFast memory holds itQ8_0GGUF · 8.2 GB · needs ~12 GB131,072 tokens
DGX H100 · 8 × 80 GBFast memory holds itQ8_0GGUF · 8.2 GB · needs ~26 GB131,072 tokens~22 GBFast memory holds itQ8_0GGUF · 8.2 GB · needs ~26 GB131,072 tokens

The file column uses the site's quant ladder (Q8_0 to Q3_K_M, MLX 8 to 4-bit on a Mac): the largest collected file whose size × 1.2 plus the context cache and the machine's reserve fits the fast memory. Planning estimates, not measured runs.

Plan another quantization or context

Consider it for

Compare Gemma 4 E4B using its publisher card. No overall score appears in the LiveBench 2026-06-25 snapshot.

Check first

The Q4 weights plus working room come to about 6 GB from 8B stated parameters, before the machine's reserve (Runs on adds it per machine). It is not a measured minimum; context, batch size, runtime and quantization change actual memory use.

Versions to download

Files you can download for this checkpoint. The section opens on the most downloaded collected GGUF source, unsloth, at Q4_K_M. On a Mac it opens on the most downloaded MLX source. Sizes are the Hub's published bytes. What is Q4?

unsloth

unsloth/gemma-4-E4B-it-GGUF · gemma-4-E4B-it-Q4_K_M.gguf · 5.0 GB

Run this file

ollama run hf.co/unsloth/gemma-4-E4B-it-GGUF:Q4_K_M
llama-server -hf unsloth/gemma-4-E4B-it-GGUF:Q4_K_M
lms get https://huggingface.co/unsloth/gemma-4-E4B-it-GGUF
  • mlx-lm: mlx-lm runs MLX repositories; pick the MLX version on a Mac

Quality scores on this page belong to the original checkpoint; these files are not scored or ranked. File sizes read 2026-10-23 · download counts read 2026-10-17 · commands: Hugging Face Hub docs: Use Ollama with any GGUF model · llama.cpp server README (-hf <user>/<model>[:quant]) · LM Studio docs: lms get with a Hugging Face URL · mlx-lm README (mlx_lm.generate --model)

Fine-tunes, adapters and other versions440 fine-tunes
Quantized versions
469
Fine-tunes
440
Adapters · merges
435 · 3

Browse them on the Hugging Face model tree · read 2026-10-23

Uncensored and abliterated versions53

Some community uploads remove the model's safety refusals. Quality may drop, the original publisher does not support them, claims about them are the uploader's, and the original license still applies. This site never recommends or ranks them.

53 derivative repositories have “uncensored” or “abliterated” in their name (read 2026-10-23).

Measured speed

No published measurement for this checkpoint

Tokens per second are shown only when a source publishes them with hardware, build and setup. They are never estimated.

How to run

The memory needed above is the Q4 load before a machine's reserve. Formula: parameters × 0.625 bytes, plus 20% working allowance; each machine then adds its system reserve: 25% of unified or system memory, 2 to 8 GB, or 2 GB per GPU on dedicated cards. This is neither measured VRAM nor checkpoint download size.

Q4 planning estimate only. Check checkpoint format, runtime support, KV cache, context, batch size and offload before choosing hardware.

Documented ways to run it

Copied as printed in the linked source (read 2026-10-18); not run by this site.

Setup stated first by the source · Transformers
pip install -U transformers torch accelerate
Transformers · model card · Getting Started
from transformers import AutoProcessor, AutoModelForMultimodalLM

MODEL_ID = "google/gemma-4-E4B-it"

# Load model
processor = AutoProcessor.from_pretrained(MODEL_ID)
model = AutoModelForMultimodalLM.from_pretrained(
    MODEL_ID,
    dtype="auto",
    device_map="auto"
)
Transformers · model card · Getting Started
# Prompt
messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Write a short joke about saving RAM."},
]

# Process input
inputs = processor.apply_chat_template(
    messages,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
    add_generation_prompt=True,
    enable_thinking=False
).to(model.device)
input_len = inputs["input_ids"].shape[-1]

# Generate output
outputs = model.generate(**inputs, max_new_tokens=1024)
response = processor.decode(outputs[0][input_len:], skip_special_tokens=False)

# Parse output
processor.parse_response(response, prefix=inputs["input_ids"])

Evidence level: Generic estimate only; no execution reproduced by this site.

Publisher sampling defaults
temperature 1 · top_p 0.95 · top_k 64generation_config.json · read 2026-10-23source
Chat template markers
tool calls · thinkingmarkers found in the template, not a test of the feature · read 2026-10-23source
Before downloading
  1. Check the exact checkpoint and license linked here.
  2. Confirm a compatible runtime and precision or quantization for your platform.
  3. Allow for context, batch size and any extra media components beyond the weights.

Technical details

What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.

Checkpoint / version
google/gemma-4-E4B-it
Task and modality
language and reasoning · text + image + audio + video
Count and basis
8B · manufacturer specificationgoogle/gemma-4-E4B-it model card (Hugging Face) · read 2026-10-17source
Context
131,072 tokens published for this modelgoogle/gemma-4-E4B-it model card (Hugging Face) · read 2026-10-17source
Architecture
Densegoogle/gemma-4-E4B-it model card (Hugging Face) · read 2026-10-17source
Released
Gemma releases (Google AI for Developers): March 31, 2026, Release of Gemma 4 in E2B, E4B, 31B and 26B A4B sizes · read 2026-10-10source
Runtime and precision
No local execution verified.
Languages
140+ languages Publisher's statement · read 2026-10-18source
Commercial use
Allowed Apache License 2.0 text (SPDX) · read 2026-10-18license text
Every stored field12 fields
Revision checked
ee0ef6023621cff504d758262d4e04895a5af4a2
Architecture
Gemma4ForConditionalGeneration
Library
transformers
Hub task tag
any-to-any
Declared base models
google/gemma-4-E4B
Formats
transformers, safetensors
Access
Open download
Publisher kind
Official
Repository created
2026-03-02creation is not the model's release
Repository updated
2026-07-20a commit is not a release date
Hub downloads (30 days) · likes
3,990,168 · 1,776this repository only · read 2026-10-25
Catalog state
Hub config or weights found; no inventory benchmark link

Google counts 4.5B effective parameters and 8B with embeddings. The extra parameters are per-layer embedding tables used as lookups, and the checkpoint stores them. The estimate uses the 8B total, not the 4.5B in the name.

Sources

Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.

Catalog reviewed: 2026-10-17. Benchmark release: 2026-06-25; snapshot collected: 2026-10-18.