Skip to content
Local AI Wizard
Your machine
Theme

Gemma 4 26B A4B vs Qwen3-VL 30B A3B for images

Two mixture-of-experts vision models that answer questions about images

Facts from the reviewed catalog

Facts from the reviewed catalog
SpecificationGemma 4 26B A4BQwen3-VL-30B-A3B-Instruct
TaskVisionVision
Parameters25.2B · 3.8B active31.1B
LicenseApache 2.0Apache 2.0
Commercial useAllowedlicense textAllowedlicense text
Quality · LMArena 2026-10-19 · vision1,242 ± 61,235–1,248 · 23,922 votes · rank 65 · sourceNot on the LMArena vision leaderboard of 2026-10-19 · source
MemoryQ4 planning estimate (~19 GB of weights before the machine's reserve)Q4 planning estimate (~24 GB of weights before the machine's reserve)
Checkpointofficial cardofficial card

Only Gemma 4 26B A4B has a result in LMArena 2026-10-19 · vision (1,242 ± 6); Qwen3-VL-30B-A3B-Instruct has none, so the two are not ranked from this source and no score is inferred for it. Blind pairwise votes by people on hosted outputs, CC BY 4.0. A rating is relative; overlapping intervals mean the order is not settled. Scale: Arena rating ± half the confidence interval.

Memory on three machines

Each machine's own reserve is added (graphics cards 2 GB; unified and system memory 25%, 2 to 8 GB). Planning estimates, not measured runs.

Gemma 4 26B A4B vs Qwen3-VL 30B A3B for images: memory on three machines
MachineGemma 4 26B A4BQwen3-VL-30B-A3B-Instruct
RTX 4090 · 24 GB VRAM~21 GBFast memory holds it~26 GBIn memory, outside the fast part · offload to PC RAM (32 GB assumed)
RTX 5090 · 32 GB VRAM~21 GBFast memory holds it~26 GBFast memory holds it
MacBook Air 13-inch M4 · 32 GB unified~27 GBFast memory holds it~32 GBFast memory holds it

Gemma 4 26B A4B: Q4 planning estimate (~19 GB of weights before the machine's reserve). Qwen3-VL-30B-A3B-Instruct: Q4 planning estimate (~24 GB of weights before the machine's reserve). Formulas

Everything that runs on each machine: RTX 4090 · 24 GB VRAM · RTX 5090 · 32 GB VRAM · MacBook Air 13-inch M4 · 32 GB unified

Which to choose

Both read an image and answer in text, both are mixtures of experts with a small active part, and both are Apache 2.0. Gemma 4 26B A4B is a general model that also chats without images; Qwen3-VL 30B A3B is Alibaba's vision-language line. Their Q4 weights take about 19 GB and 24 GB: a 24 GB card runs Gemma in its fast memory while Qwen3-VL spills over, and a 32 GB card or Mac holds both. Only Gemma 4 has a rating in the LMArena vision release; Qwen3-VL 30B A3B is not in it.

Files and run commands

The default file of the most downloaded collected source, or the commands each card documents. Not run by this site.

Gemma 4 26B A4B

unsloth/gemma-4-26B-A4B-it-GGUF · gemma-4-26B-A4B-it-UD-Q4_K_M.gguf · UD-Q4_K_M · 16.9 GB · unsloth

ollama run hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:UD-Q4_K_M
llama-server -hf unsloth/gemma-4-26B-A4B-it-GGUF:UD-Q4_K_M
lms get https://huggingface.co/unsloth/gemma-4-26B-A4B-it-GGUF
  • mlx-lm: mlx-lm runs MLX repositories; pick the MLX version on a Mac

Qwen3-VL-30B-A3B-Instruct

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 git+https://github.com/huggingface/transformers
# pip install transformers==4.57.0 # currently, V4.57.0 is not released
Transformers · model card · Using 🤗 Transformers to Chat
from transformers import Qwen3VLMoeForConditionalGeneration, AutoProcessor

# default: Load the model on the available device(s)
model = Qwen3VLMoeForConditionalGeneration.from_pretrained(
    "Qwen/Qwen3-VL-30B-A3B-Instruct", dtype="auto", device_map="auto"
)

# We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.
# model = Qwen3VLMoeForConditionalGeneration.from_pretrained(
#     "Qwen/Qwen3-VL-30B-A3B-Instruct",
#     dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

processor = AutoProcessor.from_pretrained("Qwen/Qwen3-VL-30B-A3B-Instruct")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Describe this image."},
        ],
    }
]

# Preparation for inference
inputs = processor.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_dict=True,
    return_tensors="pt"
)

# Inference: Generation of the output
generated_ids = model.generate(**inputs, max_new_tokens=128)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text)

Numbers each publisher reports

Each card's own results with its own settings. Publishers choose different tests and settings, so these values are never compared across publishers here.

Gemma 4 26B A4B · reported by Google

15 results · Google's model card · read 2026-10-25
MMLU Pro
82.6%
AIME 2026 no tools
88.3%
LiveCodeBench v6
77.1%
Codeforces ELO
1,718
GPQA Diamond
82.3%
Tau2 (average over 3)
68.2%
HLE no tools
8.7%
HLE with search
17.2%
Every reported result15
BigBench Extra Hard
64.8%
MMMLU
86.3%
MMMU Pro
73.8%Vision
OmniDocBench 1.5 (average edit distance, lower is better)
0.149Vision
MATH-Vision
82.4%Vision
MedXPertQA MM
58.1%Vision
MRCR v2 8 needle 128k (average)
44.1%Long Context

Values as printed on the card, with the publisher's own settings (card section: Benchmark Results); column “Gemma 4 26B A4B”. Not comparable across publishers and not used in any ranking. Model card

Qwen3-VL-30B-A3B-Instruct · reported by Alibaba

The publisher's card states no benchmark result for this checkpoint (read 2026-10-25). not published on the card · read 2026-10-25

Limits and dates

The published quality benchmark does not test a local quantized build. Memory estimates are not speed measurements or guaranteed hardware fits. Repository size, when available, is not VRAM. Formulas

Page updated · Catalog reviewed · LMArena 2026-10-19 · vision