Downloads · 30 days
39
11% of all-time downloads
xv0y5ncu/gemma-4-26B-A4B-it-GLQ-5bpw
gemma-4-26B-A4B-it-GLQ-5bpw is a image-text-to-text model from xv0y5ncu. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
GLQ (5.0 bits/weight) quantization of google/gemma-4-26B-A4B-it using an E8-lattice codebook + randomized Hadamard transform (RHT) + LDLQ. Weights stay compressed in memory and are dequantized on the fly by fused CUDA…
Downloads · 30 days
39
11% of all-time downloads
All-time downloads
349
Public
Parameters
10.5B
21.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors21.1 GB · 100%
How the weights are stored.
I169.2B · 87%
From the Hugging Face model README
GLQ (5.0 bits/weight) quantization of google/gemma-4-26B-A4B-it using an E8-lattice codebook + randomized Hadamard transform (RHT) + LDLQ. Weights stay compressed in memory and are dequantized on the fly by fused CUDA kernels.
Where GLQ shines: the size-vs-accuracy win is strongest at 2–4 bits/weight. At 5.0 bpw the weight savings are modest — the bigger win at this precision is pairing it with the E8 KV cache (≈4× smaller KV cache → much longer context / more concurrency in the same VRAM).
google/gemma-4-26B-A4B-itGLQ-5bpw and the bf16 base were run head-to-head on the same questions, in thinking mode (this model's intended setting):
| Benchmark | bf16 base | GLQ 5bpw |
|---|---|---|
| MMLU-Pro (n=60, paired, 16k budget) | 91.7% (55/60) | 88.3% (53/60) |
| AIME-2024 (n=30, paired, 32k budget) | 93.3% (28/30) | 90.0% (27/30) |
On this run GLQ-5bpw is 2 questions below bf16 on MMLU-Pro and 1 below on AIME-2024 — within small-n noise (95% CI ≈ ±8% MMLU-Pro, ±15% AIME), i.e. statistically indistinguishable from bf16 on these subsets, not a measured improvement or regression.
<sub>Paired, seed-fixed subsets (identical questions per precision). gemma-4 chat template, enable_thinking=True, sampling temperature=1.0, top_p=0.95, top_k=64, vLLM; single-sample pass@1 — small-n fidelity checks, not leaderboard scores. AIME-2024 used a 32k thinking budget (1/30 truncated); a 64k-budget run and the harder AIME 2025+2026 set were not completed at 5bpw. The bf16 column is carried from the same (precision-fixed) base model's paired run. The default lm-eval mmlu_pro task — no chat template, thinking off — scores ~31% for both precisions, an answer-extraction artifact; always evaluate this model in thinking mode.</sub>
python -m venv .venv
source .venv/bin/activate
pip install 'glq[vllm]' "transformers>=5.13.1,<5.15"
Pin transformers below 5.15 — 5.15.0 moved gemma-4 to a per-layer config, so
config.head_dim raises and vLLM dies before loading a single weight. Verified on
5.14.1 with vLLM 0.27.1. Not specific to GLQ: stock bf16 gemma-4 fails the same way.
from vllm import LLM, SamplingParams
def main():
llm = LLM(
model="xv0y5ncu/gemma-4-26B-A4B-it-GLQ-5bpw",
quantization="glq",
dtype="bfloat16",
max_model_len=4096,
limit_mm_per_prompt={"image": 0, "video": 0, "audio": 0}, # text-only serving
)
out = llm.generate(["The capital city of New Zealand is"],
SamplingParams(max_tokens=64, temperature=0))
print(out[0].outputs[0].text)
# The __main__ guard is REQUIRED when running this as a script. vLLM switches to the
# "spawn" multiprocessing start method once CUDA is initialised, so its worker processes
# re-import this file; without the guard the script spawns itself recursively and dies
# with "An attempt has been made to start a new process before the current process has
# finished its bootstrapping phase" -- before the model ever loads.
if __name__ == "__main__":
main()
glq registers with vLLM automatically via its plugin entry point — no extra import needed.
import glq.hf_integration # registers the GLQ quantization method
from transformers import AutoModelForImageTextToText, AutoTokenizer
import torch
model = AutoModelForImageTextToText.from_pretrained(
"xv0y5ncu/gemma-4-26B-A4B-it-GLQ-5bpw", device_map="cuda", dtype=torch.bfloat16)
tok = AutoTokenizer.from_pretrained("xv0y5ncu/gemma-4-26B-A4B-it-GLQ-5bpw")
msgs = [{"role": "user", "content": "What is the capital city of New Zealand?"}]
ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt").to("cuda")
print(tok.decode(model.generate(ids, max_new_tokens=64)[0][ids.shape[1]:], skip_special_tokens=True))
This is a multimodal base model. GLQ quantizes the text decoder (the vision/audio towers are kept in their native format). vLLM is the recommended runtime.
Serve an OpenAI-compatible endpoint, then point your agent at it:
vllm serve xv0y5ncu/gemma-4-26B-A4B-it-GLQ-5bpw --port 8000
pi-code — ~/.pi/agent/models.json:
{
"providers": {
"glq": {
"baseUrl": "http://localhost:8000/v1",
"api": "openai-completions",
"apiKey": "glq",
"models": [
{
"id": "xv0y5ncu/gemma-4-26B-A4B-it-GLQ-5bpw"
}
]
}
}
}
opencode — ~/.config/opencode/opencode.json:
{
"$schema": "https://opencode.ai/config.json",
"provider": {
"glq": {
"npm": "@ai-sdk/openai-compatible",
"name": "GLQ (local vLLM)",
"options": {
"baseURL": "http://localhost:8000/v1",
"apiKey": "glq"
},
"models": {
"xv0y5ncu/gemma-4-26B-A4B-it-GLQ-5bpw": {
"name": "gemma-4-26B-A4B-it-GLQ-5bpw"
}
}
}
}
}
GLQ also ships an E8-quantized KV cache (~4× smaller than fp16, ~bit-identical at 4-bit). Enable it at serve time:
GLQ_KV_QUANT=e8_relaxed:2 \
GLQ_KV_E8_SIDECAR=1 GLQ_KV_E8_SIDECAR_READ=1 GLQ_KV_E8_COMPRESSED_ALLOC=1 \
GLQ_KV_E8_FUSED_GATHER=1 GLQ_KV_E8_FUSED_WRITE=1 \
vllm serve xv0y5ncu/gemma-4-26B-A4B-it-GLQ-5bpw
e8_relaxed:2 ≈ 4-bit KV, :1 ≈ 2-bit, :3 ≈ 6-bit. This is the part of GLQ that keeps paying off above 4-bit weights.
GLQ compresses weights in groups of 8. A randomized Hadamard transform (a fixed random sign-flip + Hadamard rotation on each side) makes the weights and the calibration Hessian incoherent — spreading outliers so an 8-dimensional lattice quantizes them well. LDLQ then rounds each group to the nearest entry of an E8 shell codebook (a 65,536-point subset of the E8 lattice), feeding each group's rounding error forward across the remaining input dimensions via the Hessian's LDL factorization. At 5–8 bpw several stacked residual codebooks are used (N-stage residual VQ).
E8 is the 8-dimensional root lattice; the "Golay/Leech" in the project name refers to its higher-dimensional lattice cousins. Code, kernels and quantizer: GLQ on GitHub.
Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on small models) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants. Gemma 4 features a context window of up to 256K tokens and maintains multilingual support in over 140 languages.
Featuring both Dense and Mixture-of-Experts (MoE) architectures, Gemma 4 is well-suited for tasks like text generation, coding, and reasoning. The models are available in four distinct sizes: E2B, E4B, 26B A4B, and 31B. Their diverse sizes make them deployable in environments ranging from high-end phones to laptops and servers, democratizing access to state-of-the-art AI.
Gemma 4 introduces key capability and architectural advancements:
Reasoning – All models in the family are designed as highly capable reasoners, with configurable thinking modes.
Extended Multimodalities – Processes Text, Image with variable aspect ratio and resolution support (all models), Video, and Audio (featured natively on the E2B and E4B models).
Diverse & Efficient Architectures – Offers Dense and Mixture-of-Experts (MoE) variants of different sizes for scalable deployment.
Optimized for On-Device – Smaller models are specifically designed for efficient local execution on laptops and mobile devices.
Increased Context Window – The small models feature a 128K context window, while the medium models support 256K.
Enhanced Coding & Agentic Capabilities – Achieves notable improvements in coding benchmarks alongside native function-calling support, powering highly capable autonomous agents.
Native System Prompt Support – Gemma 4 introduces native support for the system role, enabling more structured and controllable conversations.
Gemma 4 models are designed to deliver frontier-level performance at each size, targeting deployment scenarios from mobile and edge devices (E2B, E4B) to consumer GPUs and workstations (26B A4B, 31B). They are well-suited for reasoning, agentic workflows, coding, and multimodal understanding.
The models employ a hybrid attention mechanism that interleaves local sliding window attention with full global attention, ensuring the final layer is always global. This hybrid design delivers the processing speed and low memory footprint of a lightweight model without sacrificing the deep awareness required for complex, long-context tasks. To optimize memory for long contexts, global layers feature unified Keys and Values, and apply Proportional RoPE (p-RoPE).
| Property | E2B | E4B | 31B Dense |
|---|---|---|---|
| Total Parameters | 2.3B effective (5.1B with embeddings) | 4.5B effective (8B with embeddings) | 30.7B |
| Layers | 35 | 42 | 60 |
| Sliding Window | 512 tokens | 512 tokens | 1024 tokens |
| Context Length | 128K tokens | 128K tokens | 256K tokens |
| Vocabulary Size | 262K | 262K | 262K |
| Supported Modalities | Text, Image, Audio | Text, Image, Audio | Text, Image |
| Vision Encoder Parameters | ~150M | ~150M | ~550M |
| Audio Encoder Parameters | ~300M | ~300M | No Audio |
The "E" in E2B and E4B stands for "effective" parameters. The smaller models incorporate Per-Layer Embeddings (PLE) to maximize parameter efficiency in on-device deployments. Rather than adding more layers or parameters to the model, PLE gives each decoder layer its own small embedding for every token. These embedding tables are large but are only used for quick lookups, which is why the effective parameter count is much smaller than the total.
| Property | 26B A4B MoE |
|---|---|
| Total Parameters | 25.2B |
| Active Parameters | 3.8B |
| Layers | 30 |
| Sliding Window | 1024 tokens |
| Context Length | 256K tokens |
| Vocabulary Size | 262K |
| Expert Count | 8 active / 128 total and 1 shared |
| Supported Modalities | Text, Image |
| Vision Encoder Parameters | ~550M |
The "A" in 26B A4B stands for "active parameters" in contrast to the total number of parameters the model contains. By only activating a 4B subset of parameters during inference, the Mixture-of-Experts model runs much faster than its 26B total might suggest. This makes it an excellent choice for fast inference compared to the dense 31B model since it runs almost as fast as a 4B-parameter model.
These models were evaluated against a large collection of different datasets and metrics to cover different aspects of text generation. Evaluation results marked in the table are for instruction-tuned models.
| Gemma 4 31B | Gemma 4 26B A4B | Gemma 4 E4B | Gemma 4 E2B | Gemma 3 27B (no think) | |
|---|---|---|---|---|---|
| MMLU Pro | 85.2% | 82.6% | 69.4% | 60.0% | 67.6% |
| AIME 2026 no tools | 89.2% | 88.3% | 42.5% | 37.5% | 20.8% |
| LiveCodeBench v6 | 80.0% | 77.1% | 52.0% | 44.0% | 29.1% |
| Codeforces ELO | 2150 | 1718 | 940 | 633 | 110 |
| GPQA Diamond | 84.3% | 82.3% | 58.6% | 43.4% | 42.4% |
| Tau2 (average over 3) | 76.9% | 68.2% | 42.2% | 24.5% | 16.2% |
| HLE no tools | 19.5% | 8.7% | - | - | - |
| HLE with search | 26.5% | 17.2% | - | - | - |
| BigBench Extra Hard | 74.4% | 64.8% | 33.1% | 21.9% | 19.3% |
| MMMLU | 88.4% | 86.3% | 76.6% | 67.4% | 70.7% |
| Vision | |||||
| MMMU Pro | 76.9% | 73.8% | 52.6% | 44.2% | 49.7% |
| OmniDocBench 1.5 (average edit distance, lower is better) | 0.131 | 0.149 | 0.181 | 0.290 | 0.365 |
| MATH-Vision | 85.6% | 82.4% | 59.5% | 52.4% | 46.0% |
| MedXPertQA MM | 61.3% | 58.1% | 28.7% | 23.5% | - |
| Audio | |||||
| CoVoST | - | - | 35.54 | 33.47 | - |
| FLEURS (lower is better) | - | - | 0.08 | 0.09 | - |
| Long Context | |||||
| MRCR v2 8 needle 128k (average) | 66.4% | 44.1% | 25.4% | 19.1% | 13.5% |
Gemma 4 models handle a broad range of tasks across text, vision, and audio. Key capabilities include:
You can use all Gemma 4 models with the latest version of Transformers. To get started, install the necessary dependencies in your environment:
pip install -U transformers torch accelerate
Once you have everything installed, you can proceed to load the model with the code below:
from transformers import AutoProcessor, AutoModelForCausalLM
MODEL_ID = "google/gemma-4-26B-A4B-it"
# Load model
processor = AutoProcessor.from_pretrained(MODEL_ID)
model = AutoModelForCausalLM.from_pretrained(
MODEL_ID,
dtype="auto",
device_map="auto"
)
Once the model is loaded, you can start generating output:
# Prompt
messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Write a short joke about saving RAM."},
]
# Process input
text = processor.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
enable_thinking=False
)
inputs = processor(text=text, return_tensors="pt").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)
To enable reasoning, set enable_thinking=True and the parse_response function will take care of parsing the thinking output.
Below, you will also find snippets for processing audio (E2B and E4B only), images, and video alongside text:
<details> <summary>Code for processing Audio</summary>Instead of using AutoModelForCausalLM, you can use AutoModelForMultimodalLM to process audio. To use it, make sure to install the following packages:
pip install -U transformers torch librosa accelerate
You can then load the model with the code below:
from transformers import AutoProcessor, AutoModelForMultimodalLM
MODEL_ID = "google/gemma-4-E2B-it"
# Load model
processor = AutoProcessor.from_pretrained(MODEL_ID)
model = AutoModelForMultimodalLM.from_pretrained(
MODEL_ID,
dtype="auto",
device_map="auto"
)
Once the model is loaded, you can start generating output by directly referencing the audio URL in the prompt:
# Prompt - add audio after text
messages = [
{
"role": "user",
"content": [
{"type": "text", "text": "Transcribe the following speech segment in its original language. Follow these specific instructions for formatting the answer:\n* Only output the transcription, with no newlines.\n* When transcribing numbers, write the digits, i.e. write 1.7 and not one point seven, and write 3 instead of three."},
{"type": "audio", "audio": "https://raw.githubusercontent.com/google-gemma/cookbook/refs/heads/main/apps/sample-data/journal1.wav"},
]
}
]
# Process input
inputs = processor.apply_chat_template(
messages,
tokenize=True,
return_dict=True,
return_tensors="pt",
add_generation_prompt=True,
).to(model.device)
input_len = inputs["input_ids"].shape[-1]
# Generate output
outputs = model.generate(**inputs, max_new_tokens=512)
response = processor.decode(outputs[0][input_len:], skip_special_tokens=False)
# Parse output
processor.parse_response(response)
</details>
<details>
<summary>Code for processing Images</summary>
Instead of using AutoModelForCausalLM, you can use AutoModelForMultimodalLM to process images. To use it, make sure to install the following packages:
pip install -U transformers torch torchvision accelerate
You can then load the model with the code below:
from transformers import AutoProcessor, AutoModelForMultimodalLM
MODEL_ID = "google/gemma-4-26B-A4B-it"
# Load model
processor = AutoProcessor.from_pretrained(MODEL_ID)
model = AutoModelForMultimodalLM.from_pretrained(
MODEL_ID,
dtype="auto",
device_map="auto"
)
Once the model is loaded, you can start generating output by directly referencing the image URL in the prompt:
# Prompt - add image before text
messages = [
{
"role": "user", "content": [
{"type": "image", "url": "https://raw.githubusercontent.com/google-gemma/cookbook/refs/heads/main/apps/sample-data/GoldenGate.png"},
{"type": "text", "text": "What is shown in this image?"}
]
}
]
# Process input
inputs = processor.apply_chat_template(
messages,
tokenize=True,
return_dict=True,
return_tensors="pt",
add_generation_prompt=True,
).to(model.device)
input_len = inputs["input_ids"].shape[-1]
# Generate output
outputs = model.generate(**inputs, max_new_tokens=512)
response = processor.decode(outputs[0][input_len:], skip_special_tokens=False)
# Parse output
processor.parse_response(response)
</details>
<details>
<summary>Code for processing Videos</summary>
Instead of using AutoModelForCausalLM, you can use AutoModelForMultimodalLM to process videos. To use it, make sure to install the following packages:
pip install -U transformers torch torchvision torchcodec librosa accelerate
You can then load the model with the code below:
from transformers import AutoProcessor, AutoModelForMultimodalLM
MODEL_ID = "google/gemma-4-26B-A4B-it"
# Load model
processor = AutoProcessor.from_pretrained(MODEL_ID)
model = AutoModelForMultimodalLM.from_pretrained(
MODEL_ID,
dtype="auto",
device_map="auto"
)
Once the model is loaded, you can start generating output by directly referencing the video URL in the prompt:
# Prompt - add video before text
messages = [
{
'role': 'user',
'content': [
{"type": "video", "video": "https://github.com/bebechien/gemma/raw/refs/heads/main/videos/ForBiggerBlazes.mp4"},
{'type': 'text', 'text': 'Describe this video.'}
]
}
]
# Process input
inputs = processor.apply_chat_template(
messages,
tokenize=True,
return_dict=True,
return_tensors="pt",
add_generation_prompt=True,
).to(model.device)
input_len = inputs["input_ids"].shape[-1]
# Generate output
outputs = model.generate(**inputs, max_new_tokens=512)
response = processor.decode(outputs[0][input_len:], skip_special_tokens=False)
# Parse output
processor.parse_response(response)
</details>
For the best performance, use these configurations and best practices:
Use the following standardized sampling configuration across all use cases:
temperature=1.0top_p=0.95top_k=64Compared to Gemma 3, the models use standard system, assistant, and user roles. To properly manage the thinking process, use the following control tokens:
<|think|> token at the start of the system prompt. To disable thinking, remove the token.<|channel>thought\n[Internal reasoning]<channel|><|channel>thought\n<channel|>[Final answer][!Note] Note that many libraries like Transformers and llama.cpp handle the complexities of the chat template for you.
For optimal performance with multimodal inputs, place:
Aside from variable aspect ratios, Gemma 4 supports variable image resolution through a configurable visual token budget, which controls how many tokens are used to represent an image. A higher token budget preserves more visual detail at the cost of additional compute, while a lower budget enables faster inference for tasks that don't require fine-grained understanding.
Use the following prompt structures for audio processing:
Transcribe the following speech segment in {LANGUAGE} into {LANGUAGE} text.
Follow these specific instructions for formatting the answer:
* Only output the transcription, with no newlines.
* When transcribing numbers, write the digits, i.e. write 1.7 and not one point seven, and write 3 instead of three.
Transcribe the following speech segment in {SOURCE_LANGUAGE}, then translate it into {TARGET_LANGUAGE}.
When formatting the answer, first output the transcription in {SOURCE_LANGUAGE}, then one newline, then output the string '{TARGET_LANGUAGE}: ', then the translation in {TARGET_LANGUAGE}.
All models support image inputs and can process videos as frames whereas the E2B and E4B models also support audio inputs. Audio supports a maximum length of 30 seconds. Video supports a maximum of 60 seconds assuming the images are processed at one frame per second.
Data used for model training and how the data was processed.
Our pre-training dataset is a large-scale, diverse collection of data encompassing a wide range of domains and modalities, which includes web documents, code, images, audio, with a cutoff date of January 2025. Here are the key components:
The combination of these diverse data sources is crucial for training a powerful multimodal model that can handle a wide variety of different tasks and data formats.
Here are the key data cleaning and filtering methods applied to the training data:
As open models become central to enterprise infrastructure, provenance and security are paramount. Developed by Google DeepMind, Gemma 4 undergoes the same rigorous safety evaluations as our proprietary Gemini models.
Gemma 4 models were developed in partnership with internal safety and responsible AI teams. A range of automated as well as human evaluations were conducted to help improve model safety. These evaluations align with Google’s AI principles, as well as safety policies, which aim to prevent our generative AI models from generating harmful content, including:
For all areas of safety testing, we saw major improvements in all categories of content safety relative to previous Gemma models. Overall, Gemma 4 models significantly outperform Gemma 3 and 3n models in improving safety, while keeping unjustified refusals low. All testing was conducted without safety filters to evaluate the model capabilities and behaviors. For both text-to-text and image-to-text, and across all model sizes, the model produced minimal policy violations, and showed significant improvements over previous Gemma models' performance.
These models have certain limitations that users should be aware of.
Multimodal models (capable of processing vision, language, and/or audio) have a wide range of applications across various industries and domains. The following list of potential uses is not comprehensive. The purpose of this list is to provide contextual information about the possible use-cases that the model creators considered as part of model training and development.
The development of vision-language models (VLMs) raises several ethical concerns. In creating an open model, we have carefully considered the following:
Risks identified and mitigations:
At the time of release, this family of models provides high-performance open vision-language model implementations designed from the ground up for responsible AI development compared to similarly sized models.
</details>Derivative work of google/gemma-4-26B-A4B-it, quantized with GLQ. It inherits the base model's license (apache-2.0) — please respect the base model's terms.