llmrun
GoogleGemma 4Gemma4ForConditionalGeneration

Gemma 4 26B A4B IT — Hardware Requirements & GPU Compatibility

VisionFunctions

Gemma 4 26B A4B IT applies a mixture-of-experts design to Google's Gemma 4 family, with roughly 26 billion total parameters but only about 4 billion active for any given token. That active-parameter count is what determines inference speed, so despite its total size the model can respond about as quickly as a much smaller dense model, though the full parameter set still needs to be held in memory, putting local use in single high-end consumer GPU territory once quantized. It also accepts image input alongside text, making it usable for multimodal chat and visual question answering. The model offers a 256K token context window, suited to long documents or extended conversations, and is released under the Apache 2.0 license for unrestricted use. Released alongside the dense 31B variant, it gives developers a faster-inference option within the same Gemma 4 generation.

25.8B params · MoE4.4B active262K contextApache 2.011.5M downloads1.6K likes3.4M quant downloads
Based on Gemma 4 26B A4B
S

Runs great on a 24 GB GPU

Runs from12 GB IQ3_S · 16KBest on24 GB Q4_K_M · ~171 tok/s · 128KMacs from32 GB ~26 tok/s

Score 105.4#37 of 92 open#6 of 34 that fit 24 GBApache 2.0

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

AOn your MacBook Pro 14" M5 (24 GB): Q4_K_M fits · 4 GB free · ~32 tok/s · up to 128K contextMacBook Pro 14" M5 (24 GB) page →

llmrun Composite Score →

105.4

Benchmarks · tier chart ↓
Among 92 open modelsHow the Composite Score is built

Run Gemma 4 26B A4B IT

Best fit for your MacBook Pro 14" M5 (24 GB). Every other method, OS and quant is in the step-by-step guide.

Recommended for your MacBook Pro 14" M5 (24 GB)

MLX
one command · needs mlx-lm installed
$mlx_lm.chat --model lmstudio-community/gemma-4-26B-A4B-it-MLX-4bit

MLX repo with its own quantisation

Download: gemma-4-26B-A4B-it-UD-Q4_K_M.gguf16.95 GBunsloth

install, OS, other quants

Other ways

each opens step-by-step

Run in cloud

Fits on RTX 3090 (24 GB) (7 GB headroom) · Q4_K_M

Generation speed
~162 tok/s
generation speed
Cost per 1M output tokens
$0.29
per 1M output tokens
Deployon Vast.aiBest optionfrom $0.17/hr (opens in new tab)
Compare GPUs →
or

How Much VRAM Does Gemma 4 26B A4B IT Need?

Select a quantization level; the listed hardware adheres to it.

QuantizationVRAM+32KOn your device
11.6 GB12.5 GB2-bit · K-quant — 2-bit quantization with K-quant improvementsFits: 256K context · ~41 tok/s
11.9 GB12.8 GB3-bit small — 3-bit small quantizationFits: 128K context · ~40 tok/s
13.2 GB14.1 GB3-bit medium — 3-bit medium quantizationFits: 128K context · ~37 tok/s
13.6 GB14.5 GB4-bit · legacy — 4-bit legacy quantizationFits: 128K context · ~36 tok/s
16.1 GB17 GB4-bit medium — 4-bit medium quantization — most popular sweet spotFits: 128K context · ~32 tok/s
19.0 GB19.9 GB5-bit medium — 5-bit medium quantization — good quality/size tradeoffFits: 32K context · ~28 tok/s
21.9 GB22.8 GB6-bit, very good — 6-bit quantization, very good qualityDoes not fit: needs 22.3 GB
26.4 GB27.4 GB8-bit, near-lossless — 8-bit quantization, near-losslessDoes not fit: needs 26.8 GB

Selected Q4_K_M

4-bit medium quantization

16.5GBat 16K context

Weights
15.5 GB
KV cache
0.7 GB
Overhead
0.3 GB

Fits MacBook Pro 14" M5 (24 GB) · 4.0 GB free · ~32 tok/s

≥50 tok/s needs ≥230 GB/s · RTX 5090 ~250, RTX 3090 Ti ~171

Which Hardware Can Run Gemma 4 26B A4B IT?

Q4_K_M · 16.1 GB

Gemma 4 26B A4B IT (Q4_K_M) requires 16.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 21+ GB is recommended. Using the full 262K context window can add up to 8.7 GB, bringing total usage to 24.8 GB. 8 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 125 devices with unified memory can run Gemma 4 26B A4B IT, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M5 Pro (24 GB).

By VRAM tier · typical GPUs and Macs at Q4_K_M
8 GB · RTX 4060Doesn't fit — smallest quant needs 8.1 GB8 GB tier →
12 GB · RTX 3060 12GBIQ3_S · 12 GB · ~99 tok/s · 16K12 GB tier →
16 GB · RTX 5060 Ti 16GBQ4_1 · 15.5 GB · ~95 tok/s · 16K16 GB tier →
24 GB · RTX 4090referenceQ4_K_M · 16.5 GB · ~171 tok/s · 128K24 GB tier →
Mac 32 GB · Mac Mini M4Q4_K_M · 16.5 GB · ~26 tok/s · 256KMacs →
Mac 64 GB · Mac Studio M4 MaxQ4_K_M · 16.5 GB · ~76 tok/s · 256KMacs →

How good is Gemma 4 26B A4B IT?

The llmrun Score merges 9 public benchmark boards into a single figure, where 100 represents the average for open models.

Score vs VRAM in the 24 GB tier

  • Gemma 4 26B A4B IT
  • Other models
  • Best Score for its VRAM

#6 of 34 that fit 24 GB24 of 34 fit your MacBook Pro 14" M5 (24 GB) (24 GB)

Each dot is a model at the best quant that fits a 24 GB GPU. The line joins the models with the best Score for their VRAM; a dot below it is beaten by a model that needs no more memory.

Full 24 GB ranking →

Benchmarks

The 6 boards that weigh most in the llmrun Score, of 11 with a result for this model; badges show who ran the test.

  • GPQA Diamond

    Epoch AI · Apr 2026Independent

    73.2%

    #29/97 open

    Independent
  • LMArena Text

    LMArena · Oct 2026Arena

    1437.6

    #23/186 open

    Arena
  • AIME 2024/2025

    Epoch AI · Apr 2026Independent

    82.2%

    #23/85 open

    Independent
  • LMArena WebDev

    LMArena · Oct 2026Arena

    1359.0

    #33/50 open

    Arena
  • SciCode

    Epoch AI · Apr 2026Lab-reported

    40.1%

    #30/65 open

    Lab-reported
  • WeirdML

    Epoch AI · Apr 2026Independent

    35.2%

    #34/46 open

    Independent
All 11 Gemma 4 26B A4B IT benchmarks

In the 24 GB class

34 models fit 24 GB

Same Score, only models that fit 24 GB at their best quant: the ranking a 24 GB owner actually chooses from.

  1. #1

    Qwen3.8 27BAlibaba

    121.5

    ~38 tok/s · 17.9 GB

  2. #2

    Qwen3.6 27BAlibaba

    111.4

    ~38 tok/s · 17.9 GB

  3. #3

    Qwen3.6 35B A3BAlibaba

    106.9

    ~151 tok/s · 22.0 GB

  4. #4

    Gemma 4 31B ITGoogle

    106.1

    ~32 tok/s · 21.7 GB

  5. #5

    Qwen3.5 35B A3BAlibaba

    105.6

    ~151 tok/s · 22.0 GB

  6. #6

    Gemma 4 26B A4B ITGoogle

    105.4

    ~171 tok/s · 16.5 GB

Full 24 GB ranking →RTX 4090 page →

Alternatives to Gemma 4 26B A4B IT

Gemma 4 family · 35 models →

Official models with an llmrun Score, each answering one question; numbers are at the best quant that fits a 24 GB GPU.

Similar models

10
ModelScoreVRAMtok/sWhy it is similar
Qwen3.6 35B A3BAlibaba106.922 GB~151similar score
Gemma 4 31B ITGoogle106.121.7 GB~32similar score
Qwen3.5 35B A3BAlibaba105.622 GB~151similar score
Qwen3.5 27BAlibaba103.817.9 GB~38similar score
Seed OSS 36B InstructByteDance-Seed102.522.8 GB~31similar score
Qwen3 30B A3B Thinking 2507Alibaba100.619.4 GB~173similar score
Qwen3.5 9BAlibaba99.46.6 GB~103similar score
Qwen3 32BAlibaba98.422.6 GB~32similar score
Qwen3 14BAlibaba97.911.9 GB~69similar score
DeepSeek R1 Distill Qwen 32BDeepSeek97.023 GB~34similar score
Fine-tunes & variants(9)

Specifications

Publisher
Google
Family
Gemma 4
Parameters
25.8B
Active parameters
4.4B per token
Architecture
Gemma4ForConditionalGeneration
Context Length
262,144 tokens
Vocabulary Size
262,144
Release Date
2026-03-11
License
Apache 2.0

Resources

Frequently Asked Questions

How much VRAM does Gemma 4 26B A4B IT need?

Gemma 4 26B A4B IT requires 16.1 GB of VRAM at Q4_K_M, or 52.3 GB at BF16. Full 262K context adds up to 8.7 GB (24.8 GB total).

VRAM = Weights + KV Cache + Overhead

Weights = 25.8B × 4.8 bits ÷ 8 = 15.5 GB

KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)

Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.

KV Cache + Overhead ≈ 9.3 GB (at full 262K context)

VRAM usage by quantization

16.1 GB
24.8 GB

Learn more about VRAM estimation →

Can NVIDIA GeForce RTX 4090 run Gemma 4 26B A4B IT?

Yes, at Q6_K (21.9 GB) or lower. Higher quantizations like Q8_0 (26.4 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.

What's the best quantization for Gemma 4 26B A4B IT?

For Gemma 4 26B A4B IT, Q4_K_M (16.1 GB) offers the best balance of quality and VRAM usage. Q4_K_L (16.4 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 7.7 GB.

VRAM requirement by quantization

IQ2_XXS
7.7 GB
IQ3_S
11.6 GB
Q3_K_L
13.9 GB
Q4_K_M ★
16.1 GB
Q5_0
16.8 GB
BF16
52.3 GB

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run Gemma 4 26B A4B IT on a Mac?

Yes, but only at lower quantizations. The smallest Mac that can run Gemma 4 26B A4B IT is iPad Pro M5 13" (16 GB) at IQ2_XXS; 136 of the 156 Macs we list can run it at some quantization. For Q4_K_M (16.1 GB) you need a Mac with more unified memory.

Can I run Gemma 4 26B A4B IT locally?

Yes — Gemma 4 26B A4B IT can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is Gemma 4 26B A4B IT?

At Q4_K_M, Gemma 4 26B A4B IT can reach ~152 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~171 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.

tok/s = 1000 ÷ (active GB ÷ (bandwidth GB/s × efficiency) × 1000 + layers × routing ms)

Mixture-of-Experts: just the active experts get read for each token, along with a fixed routing cost per layer.

Example: NVIDIA B200 → 2.7 GB active ÷ (8000 × 0.65) = 0.53 ms, plus 30 layers × 0.055 ms = 1.65 ms, so 1000 ÷ 2.18 ms = ~459 tok/s

Estimated speed at Q4_K_M (16.1 GB)

~459 tok/s
~171 tok/s
~459 tok/s
~398 tok/s

Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.

Learn more about tok/s estimation →

What's the download size of Gemma 4 26B A4B IT?

At Q4_K_M, the download is about 15.48 GB. The full-precision BF16 version is 51.61 GB. The smallest option (IQ2_XXS) is 7.10 GB.

Which GPUs can run Gemma 4 26B A4B IT?

8 consumer GPUs can run Gemma 4 26B A4B IT at Q4_K_M. Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU have plenty of headroom for comfortable inference.

Which devices can run Gemma 4 26B A4B IT?

125 devices with unified memory can run Gemma 4 26B A4B IT at Q4_K_M (16.1 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.