Total runs:
349.1K
Run Growth:
266.7K
Growth Rate:
77.96%
Sponsored by
PoYo.AI
AtomicChat / gemma-4-E4B-it-GGUF
Model's Last Updated: July 24 2026
image-text-to-text
Introduction of gemma-4-E4B-it-GGUF
Model Details of gemma-4-E4B-it-GGUF
Gemma 4 E4B , self-quantized to GGUF by Atomic Chat . Built straight from Google's original weights with a per-tensor importance matrix. Runs fully offline.
Highlights
- Natively multimodal — handles text, image, and audio input and generates text output.
- 4.5B effective parameters (8B with embeddings) — the "E" stands for "effective", using Per-Layer Embeddings (PLE) for on-device efficiency.
- 128K-token context window built on a hybrid local/global attention mechanism.
-
Built-in thinking mode
— configurable step-by-step reasoning, triggered with the
<|think|>token. - Native function calling for structured tool use and agentic workflows.
- Multilingual — out-of-the-box support for 35+ languages, pre-trained on 140+ languages.
These GGUFs are self-quantized from the original weights , not a repack. The importance matrix keeps low-bit quants closer to the full-precision model.
Always pass
--jinjaso the Gemma 4 E4B chat template is applied. Without it the model can emit malformed turns.
Model Overview
| Property | Value |
|---|---|
| Base model |
google/gemma-4-E4B-it
|
| Parameters | 4.5B effective (8B with embeddings); uses Per-Layer Embeddings (PLE) |
| Layers | 42 |
| Context length | 128K tokens |
| Vocabulary | 262K |
| Modalities | Text, Image, Audio |
| Architecture | Dense, hybrid local sliding-window (512) + global attention with p-RoPE |
| This repo | GGUF quants (imatrix) + vision mmproj |
Gemma 4 E4B is multimodal. This repo ships the
mmproj-gemma4-e4b-it-f16.ggufvision projector. With-hfit is pulled automatically; otherwise pass--mmproj. Usellama-mtmd-cliorllama-serverto feed images.
Scores are Google's published results for the base
google/gemma-4-E4B-it
. Quantization preserves the large majority of this;
Q4_K_M
and up sit within a point or two of full precision.
Choosing a quant
| Quant | Size | Notes |
|---|---|---|
Q2_K
|
4.4 GB | Smallest. Minimal RAM, clear quality drop. |
IQ3_M
|
4.7 GB | Beats Q3 at similar size thanks to imatrix. Best low-RAM pick. |
Q3_K_M
|
4.9 GB | Low quality but usable. |
Q3_K_L
|
5.0 GB | A step above Q3_K_M. |
IQ4_XS
|
5.1 GB | Excellent quality for size. Recommended low-bit. |
Q4_K_S
|
5.2 GB | Compact Q4, fast. |
Q4_K_M
|
5.3 GB | Recommended default. Best balance of size, speed and quality. |
UD-Q4_K_XL
|
6.2 GB | Dynamic. Embeddings and output kept at Q8_0 for higher quality at a Q4 footprint. |
Q5_K_S
|
5.7 GB | Higher quality. |
Q5_K_M
|
5.8 GB | Higher quality, low loss. |
Q6_K
|
6.2 GB | Near lossless. |
Q8_0
|
8.0 GB | Effectively lossless, reference quality. |
Pick the largest file that fits your (V)RAM with room for context.
Q4_K_MorUD-Q4_K_XLis the sweet spot for most setups;Q6_KorQ8_0for maximum fidelity.
Get started
Run Gemma 4 E4B locally with:
-
Atomic Chat
:
the easiest path. Open the app, search
AtomicChat/gemma4-e4b-it-GGUF, pick a quant, hit Use this model . -
llama.cpp:
llama-server -hf AtomicChat/gemma4-e4b-it-GGUF:Q4_K_M --jinja -c 8192 -
Ollama:
ollama run hf.co/AtomicChat/gemma4-e4b-it-GGUF:Q4_K_M - LM Studio / Jan: search the repo id, download any quant.
Best practices
| Parameter | Value |
|---|---|
| temperature | 1.0 |
| top_p | 0.95 |
| top_k | 64 |
Google's standardized sampling configuration recommended across all use cases.
Run in llama.cpp
git clone https://github.com/ggerganov/llama.cpp
cmake llama.cpp -B llama.cpp/build -DBUILD_SHARED_LIBS=OFF -DGGML_CUDA=ON
cmake --build llama.cpp/build --config Release -j --target llama-cli llama-server
./llama.cpp/build/bin/llama-server \
-hf AtomicChat/gemma4-e4b-it-GGUF:UD-Q4_K_XL \
--jinja -ngl 99 -c 8192 -fa on
How these were made
-
Download
google/gemma-4-E4B-it(original weights). - Convert to f16 GGUF with llama.cpp .
-
Build an importance matrix over
calibration_datav3(100 chunks). -
Quantize the full ladder with
--imatrix. -
UD-Q4_K_XLadditionally pins the token-embedding and output tensors toQ8_0.
License
Original model by Google DeepMind, released under the Apache 2.0 license. Quantized by Atomic Chat.
Runs of AtomicChat gemma-4-E4B-it-GGUF on huggingface.co
3.7K
Total runs
-52
24-hour runs
22
3-day runs
656
7-day runs
-2.2K
30-day runs
More Information About gemma-4-E4B-it-GGUF huggingface.co Model
Url of gemma-4-E4B-it-GGUF
gemma-4-E4B-it-GGUF huggingface.co Url
Provider of gemma-4-E4B-it-GGUF huggingface.co
Other API from AtomicChat
Updated:August 09 2026
Total runs:
206.3K
Run Growth:
174.1K
Growth Rate:
70.58%
Total runs:
197.8K
Run Growth:
170.7K
Growth Rate:
100.00%
Total runs:
95.6K
Run Growth:
85.9K
Growth Rate:
90.40%
Total runs:
73.4K
Run Growth:
46.3K
Growth Rate:
62.93%
Total runs:
73.1K
Run Growth:
45.4K
Growth Rate:
61.84%
Total runs:
72.9K
Run Growth:
44.7K
Growth Rate:
61.07%
Total runs:
63.5K
Run Growth:
59.9K
Growth Rate:
95.13%
Total runs:
6.6K
Run Growth:
1.4K
Growth Rate:
20.97%
Total runs:
5.1K
Run Growth:
-212
Growth Rate:
-4.10%
Total runs:
4.3K
Run Growth:
-3.3K
Growth Rate:
-74.23%
Total runs:
4.2K
Run Growth:
-13.6K
Growth Rate:
-320.40%
Total runs:
4.1K
Run Growth:
-8.2K
Growth Rate:
-199.66%
Total runs:
3.7K
Run Growth:
-10.6K
Growth Rate:
-284.91%
Total runs:
3.2K
Run Growth:
-17.0K
Growth Rate:
-461.43%
Total runs:
3.0K
Run Growth:
-2.3K
Growth Rate:
-76.81%
Total runs:
2.9K
Run Growth:
629
Growth Rate:
21.50%
Total runs:
2.9K
Run Growth:
-101
Growth Rate:
-3.61%
Total runs:
2.5K
Run Growth:
-1.4K
Growth Rate:
-59.41%
Total runs:
2.3K
Run Growth:
-8.7K
Growth Rate:
-388.16%
Total runs:
2.2K
Run Growth:
463
Growth Rate:
21.59%
Total runs:
2.0K
Run Growth:
-13.9K
Growth Rate:
-660.76%
Total runs:
1.8K
Run Growth:
803
Growth Rate:
43.27%
Total runs:
1.8K
Run Growth:
-14.7K
Growth Rate:
-795.04%
Total runs:
1.7K
Run Growth:
657
Growth Rate:
37.65%
Total runs:
1.7K
Run Growth:
1.6K
Growth Rate:
100.00%
Total runs:
1.6K
Run Growth:
-563
Growth Rate:
-35.72%
Total runs:
1.6K
Run Growth:
1.6K
Growth Rate:
100.00%
Total runs:
1.5K
Run Growth:
720
Growth Rate:
45.80%
Total runs:
1.2K
Run Growth:
1.2K
Growth Rate:
100.00%
Total runs:
1.1K
Run Growth:
-99
Growth Rate:
-8.56%
Total runs:
1.1K
Run Growth:
-2.0K
Growth Rate:
-172.03%
Total runs:
1.1K
Run Growth:
-1.0K
Growth Rate:
-96.64%
Total runs:
1.1K
Run Growth:
1.0K
Growth Rate:
100.00%
Total runs:
1.0K
Run Growth:
1.0K
Growth Rate:
100.00%
Total runs:
1.0K
Run Growth:
1.0K
Growth Rate:
100.00%
Total runs:
727
Run Growth:
-77
Growth Rate:
-10.48%
Total runs:
635
Run Growth:
565
Growth Rate:
100.00%
Total runs:
632
Run Growth:
-3.5K
Growth Rate:
-560.38%
Total runs:
609
Run Growth:
-7.6K
Growth Rate:
-1212.84%
Total runs:
603
Run Growth:
-54
Growth Rate:
-8.97%
Total runs:
602
Run Growth:
602
Growth Rate:
100.00%
Total runs:
594
Run Growth:
-3.3K
Growth Rate:
-557.93%
Total runs:
590
Run Growth:
585
Growth Rate:
100.00%
Total runs:
565
Run Growth:
65
Growth Rate:
11.73%
Total runs:
525
Run Growth:
-220
Growth Rate:
-41.20%
Total runs:
521
Run Growth:
160
Growth Rate:
32.06%
Total runs:
512
Run Growth:
-1.2K
Growth Rate:
-247.61%
Total runs:
456
Run Growth:
-553
Growth Rate:
-118.92%
Total runs:
429
Run Growth:
-426
Growth Rate:
-99.30%
Total runs:
416
Run Growth:
411
Growth Rate:
100.00%
Total runs:
413
Run Growth:
-1.3K
Growth Rate:
-307.13%
Total runs:
384
Run Growth:
332
Growth Rate:
86.46%
Total runs:
382
Run Growth:
-250
Growth Rate:
-63.94%
Total runs:
381
Run Growth:
-1.4K
Growth Rate:
-343.70%
Total runs:
313
Run Growth:
240
Growth Rate:
78.69%
Total runs:
303
Run Growth:
297
Growth Rate:
100.00%
Total runs:
295
Run Growth:
293
Growth Rate:
100.00%
Total runs:
293
Run Growth:
-629
Growth Rate:
-214.68%
Total runs:
292
Run Growth:
286
Growth Rate:
100.00%
Total runs:
285
Run Growth:
-142
Growth Rate:
-50.35%
Total runs:
267
Run Growth:
-340
Growth Rate:
-126.39%
Total runs:
250
Run Growth:
-1.5K
Growth Rate:
-593.23%
Total runs:
247
Run Growth:
-500
Growth Rate:
-204.08%
Total runs:
235
Run Growth:
233
Growth Rate:
100.00%
Total runs:
224
Run Growth:
-845
Growth Rate:
-378.92%
Total runs:
220
Run Growth:
-1.5K
Growth Rate:
-667.11%
Total runs:
219
Run Growth:
-232
Growth Rate:
-120.83%
Total runs:
218
Run Growth:
-58
Growth Rate:
-26.13%
Total runs:
208
Run Growth:
204
Growth Rate:
100.00%
Total runs:
192
Run Growth:
-162
Growth Rate:
-84.38%
Total runs:
191
Run Growth:
-6.4K
Growth Rate:
-2927.06%
Total runs:
159
Run Growth:
-641
Growth Rate:
-381.55%
Total runs:
152
Run Growth:
-899
Growth Rate:
-558.39%
Total runs:
135
Run Growth:
-701
Growth Rate:
-511.68%
Total runs:
135
Run Growth:
-273
Growth Rate:
-202.22%
Total runs:
135
Run Growth:
-121
Growth Rate:
-88.32%
Total runs:
134
Run Growth:
-376
Growth Rate:
-278.52%
Total runs:
120
Run Growth:
-457
Growth Rate:
-380.83%
Total runs:
117
Run Growth:
117
Growth Rate:
100.00%
Total runs:
117
Run Growth:
-869
Growth Rate:
-689.68%
Total runs:
117
Run Growth:
104
Growth Rate:
88.89%
Total runs:
106
Run Growth:
-745
Growth Rate:
-677.27%
Total runs:
105
Run Growth:
-795
Growth Rate:
-750.00%
Total runs:
104
Run Growth:
-1.0K
Growth Rate:
-986.54%
Total runs:
104
Run Growth:
-216
Growth Rate:
-201.87%
Total runs:
101
Run Growth:
-899
Growth Rate:
-848.11%
Total runs:
100
Run Growth:
-383
Growth Rate:
-375.49%
Total runs:
94
Run Growth:
82
Growth Rate:
87.23%
Total runs:
93
Run Growth:
-1.2K
Growth Rate:
-1240.63%
Total runs:
82
Run Growth:
-409
Growth Rate:
-486.90%
Total runs:
78
Run Growth:
-960
Growth Rate:
-1215.19%
Total runs:
65
Run Growth:
-11
Growth Rate:
-16.92%
Total runs:
64
Run Growth:
-28
Growth Rate:
-43.75%
Total runs:
57
Run Growth:
-32
Growth Rate:
-56.14%
Total runs:
47
Run Growth:
-1
Growth Rate:
-2.13%
Total runs:
45
Run Growth:
-14
Growth Rate:
-31.11%