Gemma 3 27B IT — Hardware Requirements & GPU Compatibility
VisionChat
Gemma 3 27B IT is a 27B-parameter open language model from tripolskypetr in the Gemma 3 family. It supports a context window of up to 131,072 tokens. At Q4_K_M it needs about 17.87 GB of VRAM — see which GPUs and Macs can run it below.
Runs well on a 24 GB GPU
Runs from 12 GB (IQ2_XXS · 16K)Best on 24 GB (Q4_K_M · ~37 tok/s · 32K)Macs from 16 GB (IQ2_M · ~13 tok/s)
Gemma Terms
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Gemma 3 27B IT
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
vllm serve tripolskypetr/gemma-3-27b-it --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3090 (24 GB) (4 GB headroom) · Q4_K_M
- Generation speed
- ~34 tok/s
- generation speed
- Cost per 1M output tokens
- $1.61
- per 1M output tokens
How Much VRAM Does Gemma 3 27B IT Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 13.1 GB | 16.9 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 64K context · ~50 tok/s | |
| 13.5 GB | 17.2 GB | 3-bit small — 3-bit small quantization | Fits: 64K context · ~49 tok/s | |
| 14.8 GB | 18.6 GB | 3-bit medium — 3-bit medium quantization | Fits: 64K context · ~44 tok/s | |
| 15.2 GB | 18.9 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 64K context · ~43 tok/s | |
| 17.9 GB | 21.6 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 32K context · ~37 tok/s | |
| 20.9 GB | 24.7 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 16K context · ~31 tok/s | |
| 23.9 GB | 27.7 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 4K context · ~27 tok/s | |
| 28.7 GB | 32.4 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 30.1 GB |
Selected Q4_K_M
4-bit medium quantization19.3GBat 16K context
- Weights
- 16.2 GB
- KV cache
- 2.8 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 4.7 GB free · ~37 tok/s
≥50 tok/s needs ≥1.37 TB/s · RTX 5090 ~65
Which Hardware Can Run Gemma 3 27B IT?
Q4_K_M · 17.9 GBGemma 3 27B IT (Q4_K_M) requires 17.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 24+ GB is recommended. Using the full 131K context window can add up to 17.5 GB, bringing total usage to 35.4 GB. 8 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 122 devices with unified memory can run Gemma 3 27B IT, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Mini M5 Pro (24 GB).
20 GB
fits · 0.7 GB free · up to 16K ctx
1 GPU
RX 7900 XT~27Simulate output on RX 7900 XT32–40 GB
fits · 12.7 GB free · up to 64K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~65Simulate output on RTX 5090M5 Max36 GB~18Simulate output on Mac Studio M5 Max (36 GB)M532 GB~6Simulate output on MacBook Air 13" M5 (32 GB)Orin~7Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~5Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Gemma 3 27B IT
Gemma 3 family · 20 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Qwen3.8 27BAlibaba | 122.0 | 17.9 GB | ~38 | same size |
| Qwen3.6 27BAlibaba | 111.2 | 17.9 GB | ~38 | same size |
| Qwen3.5 27BAlibaba | 103.8 | 17.9 GB | ~38 | same size |
| Gemma 2 27B ITGoogle | 72.7 | 19.5 GB | ~37 | same size |
| Gemma 4 26B A4BGoogle | — | 16.5 GB | ~171 | same size |
| Ariarhymes-ai | — | 20.2 GB | ~168 | same size |
Specifications
- Publisher
- tripolskypetr
- Family
- Gemma 3
- Parameters
- 27B
- Architecture
- Gemma3ForConditionalGeneration
- Context Length
- 131,072 tokens
- Vocabulary Size
- 262,208
- Release Date
- 2025-06-05
- License
- Gemma Terms
Frequently Asked Questions
How much VRAM does Gemma 3 27B IT need?
Gemma 3 27B IT requires 17.9 GB of VRAM at Q4_K_M, or 55.7 GB at BF16. Full 131K context adds up to 17.5 GB (35.4 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 27B × 4.8 bits ÷ 8 = 16.2 GB
KV Cache + Overhead ≈ 1.7 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 ≈ 19.2 GB (at full 131K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 4090 run Gemma 3 27B IT?
Yes, at Q6_K (23.9 GB) or lower. Higher quantizations like Q8_0 (28.7 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
What's the best quantization for Gemma 3 27B IT?
For Gemma 3 27B IT, Q4_K_M (17.9 GB) offers the best balance of quality and VRAM usage. Q5_K_S (20.2 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 9.1 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Gemma 3 27B IT on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run Gemma 3 27B IT, the smallest at IQ2_M. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 17.9 GB of usable unified memory (RAM minus macOS overhead), from Mac Mini M5 Pro (24 GB).
Can I run Gemma 3 27B IT locally?
Yes — Gemma 3 27B IT can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Gemma 3 27B IT?
At Q4_K_M, Gemma 3 27B IT can reach ~269 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~37 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 ÷ 17.9 × 0.65 = ~291 tok/s
Estimated speed at Q4_K_M (17.9 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Gemma 3 27B IT?
At Q4_K_M, the download is about 16.20 GB. The full-precision BF16 version is 54.00 GB. The smallest option (IQ2_XXS) is 7.43 GB.
Which GPUs can run Gemma 3 27B IT?
8 consumer GPUs can run Gemma 3 27B IT at Q4_K_M. Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU has plenty of headroom for comfortable inference.
Which devices can run Gemma 3 27B IT?
122 devices with unified memory can run Gemma 3 27B IT at Q4_K_M (17.9 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (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.