Gemma 4 26B A4B IT — Hardware Requirements & GPU Compatibility
Vision
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.
10.5M downloads
1.5K likesSpecifications
- Publisher
- Family
- Gemma 4
- Parameters
- 25.8B
- 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_Kest. | 3.40 | 11.6 GB | 55.6 GB | 10.97 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 13.2 GB | 57.2 GB | 12.58 GB | 3-bit medium quantization |
| Q4_K_Mest. | 4.80 | 16.1 GB | 60.1 GB | 15.48 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 19.0 GB | 63.0 GB | 18.39 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 21.9 GB | 65.9 GB | 21.29 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 26.4 GB | 70.4 GB | 25.81 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 52.3 GB | 96.2 GB | 51.61 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run Gemma 4 26B A4B IT?
Q4_K_M · 16.1 GBGemma 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 44.0 GB, bringing total usage to 60.1 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 · 16.1 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.
Benchmarks
Benchmark details →Related Models
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 44.0 GB (60.1 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)
KV Cache + Overhead ≈ 44.6 GB (at full 262K context)
VRAM usage by quantization
Q4_K_M16.1 GBQ4_K_M + full context60.1 GB- 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. Q5_K_M (19.0 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 11.6 GB.
VRAM requirement by quantization
Q2_K11.6 GBQ4_K_M ★16.1 GBQ5_K_M19.0 GBQ6_K21.9 GBQ8_026.4 GBBF1652.3 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 11.6 GB at Q2_K, 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 16.1 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 ~153 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~183 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 ÷ 16.1 × 0.65 = ~469 tok/s
Estimated speed at Q4_K_M (16.1 GB)
~469 tok/s~183 tok/s~469 tok/s~411 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 15.48 GB. The full-precision BF16 version is 51.61 GB. The smallest option (Q2_K) is 10.97 GB.
- Which GPUs can run Gemma 4 26B A4B IT?
8 consumer GPUs can run Gemma 4 26B A4B IT at Q4_K_M (16.1 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 (16.1 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.