Z Image Turbo — Hardware Requirements & GPU Compatibility
Chat
Z Image Turbo is a 6.2B-parameter open language model from Tongyi-MAI. At BF16 it needs about 13.54 GB of VRAM — see which GPUs and Macs can run it below.
Runs well on a 24 GB GPU
Runs from 16 GB (BF16 · 16K)Best on 24 GB (BF16 · ~48 tok/s · 32K)Macs from 18 GB (BF16 · ~8 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Z Image Turbo
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve Tongyi-MAI/Z-Image-Turbo --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX A5000 (24 GB) (8 GB headroom) · BF16
- Generation speed
- ~37 tok/s
- generation speed
- Cost per 1M output tokens
- $1.20
- per 1M output tokens
How Much VRAM Does Z Image Turbo Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 13.5 GB | 18.7 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 32K context · ~48 tok/s |
Selected BF16
Brain floating point 1615.9GBat 16K context
- Weights
- 12.9 GB
- KV cache
- 2.7 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 8.1 GB free · ~48 tok/s
≥50 tok/s needs ≥1.04 TB/s · RTX 5090 ~86
Which Hardware Can Run Z Image Turbo?
BF16 · 13.5 GBZ Image Turbo (BF16) requires 13.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 18+ GB is recommended. 26 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 5080. 124 devices with unified memory can run Z Image Turbo, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), MacBook Pro 14" M3 Pro (18 GB).
16–18 GB
16–18 GB tier →fits · 0.1 GB free · up to 16K ctx
18 GPUs · 1 Mac class
RTX 5080~46Simulate output on RTX 5080RTX 5070 Ti~43Simulate output on RTX 5070 TiRTX 4080 SUPER~35Simulate output on RTX 4080 SUPERM3 Pro*18 GB~8Simulate output on MacBook Pro 14" M3 Pro (18 GB)20 GB
fits · 4.1 GB free · up to 32K ctx
1 GPU
RX 7900 XT~36Simulate output on RX 7900 XT32–40 GB
fits · 16.1 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~86Simulate output on RTX 5090M5 Max36 GB~24Simulate output on Mac Studio M5 Max (36 GB)M532 GB~8Simulate output on MacBook Air 13" M5 (32 GB)Orin~10Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~7Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at BF16
Similar models
3| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Yi 6B Chat01.AI | — | 4.2 GB | ~161 | same size |
| Chatglm3 6BZ.ai | — | 5.2 GB | ~159 | same size |
| Yi 1.5 6B Chat01.AI | — | 4.2 GB | ~161 | same size |
Fine-tunes & variants(1)
Frequently Asked Questions
How much VRAM does Z Image Turbo need?
Z Image Turbo requires 13.5 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 6.2B × 16 bits ÷ 8 = 12.3 GB
KV Cache + Overhead ≈ 1.2 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.
VRAM usage by quantization
Can I run Z Image Turbo on a Mac?
Yes — MacBook Pro 14" M3 Pro (18 GB) and 108 other Macs can run Z Image Turbo. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 13.5 GB of usable unified memory (RAM minus macOS overhead).
Can I run Z Image Turbo locally?
Yes — Z Image Turbo can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Z Image Turbo?
At BF16, Z Image Turbo can reach ~355 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~48 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 ÷ 13.54 × 0.65 = ~384 tok/s
Estimated speed at BF16 (13.5 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Z Image Turbo?
At BF16, the download is about 12.31 GB.
Which GPUs can run Z Image Turbo?
26 consumer GPUs can run Z Image Turbo at BF16. Top options include AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3090 Ti, AMD Radeon RX 6800. 7 GPUs have plenty of headroom for comfortable inference.
Which devices can run Z Image Turbo?
124 devices with unified memory can run Z Image Turbo at BF16 (13.5 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.