Gemma 4 26B A4B IT — Hardware Requirements & GPU Compatibility
Vision
Gemma 4 26B A4B IT is a 26.5B-parameter open language model from Google in the Gemma 4 family. It supports a context window of up to 262,144 tokens. At Q4_K_M it needs about 16.57 GB of VRAM — see which GPUs and Macs can run it below.
13.2M downloads
1.3K likesSpecifications
- Publisher
- Family
- Gemma 4
- Parameters
- 26.5B
- Architecture
- Gemma4ForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 262,144
- Release Date
- 2026-03-11
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Gemma 4 26B A4B IT Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 11.9 GB | 55.9 GB | 11.28 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 12.3 GB | 56.2 GB | 11.61 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 13.6 GB | 57.5 GB | 12.94 GB | 3-bit medium quantization |
| Q4_K_M | 4.80 | 16.6 GB | 60.5 GB | 15.93 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 19.6 GB | 63.5 GB | 18.91 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 22.5 GB | 66.5 GB | 21.90 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 27.2 GB | 71.1 GB | 26.54 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run Gemma 4 26B A4B IT?
Q4_K_M · 16.6 GBGemma 4 26B A4B IT (Q4_K_M) requires 16.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 22+ GB is recommended. Using the full 262K context window can add up to 44.0 GB, bringing total usage to 60.5 GB. 8 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroom
Which Devices Can Run Gemma 4 26B A4B IT?
Q4_K_M · 16.6 GB41 devices with unified memory can run Gemma 4 26B A4B IT, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightWhere to Download Gemma 4 26B A4B IT
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Related Models
Frequently Asked Questions
- How much VRAM does Gemma 4 26B A4B IT need?
Gemma 4 26B A4B IT requires 16.6 GB of VRAM at Q4_K_M, or 53.7 GB at BF16. Full 262K context adds up to 44.0 GB (60.5 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 26.5B × 4.8 bits ÷ 8 = 15.9 GB
KV Cache + Overhead ≈ 0.7 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 44.6 GB (at full 262K context)
VRAM usage by quantization
Q4_K_M16.6 GBQ4_K_M + full context60.5 GB- Can NVIDIA GeForce RTX 4090 run Gemma 4 26B A4B IT?
Yes, at Q6_K (22.5 GB) or lower. Higher quantizations like Q8_0 (27.2 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 (16.6 GB) offers the best balance of quality and VRAM usage. Q5_K_S (18.9 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 8.0 GB.
VRAM requirement by quantization
IQ2_XXS8.0 GBQ2_K11.9 GBIQ4_XS14.9 GBQ4_K_M ★16.6 GBQ5_K_S18.9 GBBF1653.7 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Gemma 4 26B A4B IT on a Mac?
Gemma 4 26B A4B IT requires at least 8.0 GB at IQ2_XXS, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Gemma 4 26B A4B IT locally?
Yes — Gemma 4 26B A4B IT can run locally on consumer hardware. At Q4_K_M quantization it needs 16.6 GB of VRAM. 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 ~266 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~40 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 16.6 × 0.65 = ~314 tok/s
Estimated speed at Q4_K_M (16.6 GB)
~314 tok/s~40 tok/s~314 tok/s~266 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Gemma 4 26B A4B IT?
At Q4_K_M, the download is about 15.93 GB. The full-precision BF16 version is 53.09 GB. The smallest option (IQ2_XXS) is 7.30 GB.
- Which GPUs can run Gemma 4 26B A4B IT?
8 consumer GPUs can run Gemma 4 26B A4B IT at Q4_K_M (16.6 GB). 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?
41 devices with unified memory can run Gemma 4 26B A4B IT at Q4_K_M (16.6 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.