Best larger-system route
Studio 96
The smallest system in the range that reaches this model's preferred working allowance.
Explore Studio 96Wan AI model
Wan2.2 Hardware Requirements & GPU Server Fit
Wan documents a minimum 24GB GPU for 720p generation with model offload, dtype conversion and the text encoder on CPU. Team 32 clears that floor. An 80GB-class GPU can remove those offload options for faster execution.
- Model version
Wan-AI/Wan2.2-TI2V-5B- Family and variant
- Wan2.2 TI2V 5B · Wan2.2-TI2V-5B
- Source version
921dbaf3f167- Source updated
- 7 August 2025
Wan AI Wan2.2 TI2V 5B
Wan-AI/Wan2.2-TI2V-5B - Minimum GPU memory
- 24GB VRAM with documented CPU offload settings
- Recommended hardware
- 80GB or more to remove the documented offload options
- Licence
- Apache License 2.0
- Useful for
- Video generation
Buyer verdict
Where Wan2.2 TI2V 5B is a sensible fit
Wan2.2 TI2V 5B is a practical starting point for local video generation because it has an official 24GB minimum and a 720p workflow.
These figures apply to the named model version. Quantisation, fine-tuning, context length, image resolution, batch size and serving software can materially change the hardware needed.
Hardware requirements
- Minimum
- 24GB VRAM with documented CPU offload settings
- Recommended
- 80GB or more to remove the documented offload options
This is the official 720p command profile.
Wan states this can speed execution; actual latency still needs measurement.
Technical specification
Wan2.2 TI2V 5B model and hardware facts
Specifications shown for source version
921dbaf3f1674a56f47e83fb80a34bac8a8f203e, updated
7 August 2025.
- Parameters
- 5B
- Tasks
- Text-to-video + image-to-video
- Official minimum
- 24GB VRAM with offload
- No-offload guidance
- 80GB VRAM or more
- Resolution
- 1280 × 704 or 704 × 1280
- Licence
- Apache 2.0
Product compatibility
Wan2.2 TI2V 5B compatibility across all 11 GPU systems
- Systems that fit without model splitting
- 11
- Systems needing multi-GPU validation
- 0
A system is listed as fitting when its GPU memory meets the requirement shown above. Speed, usable context, batch size and concurrent users still need testing with the final model and software configuration.
sme workstation
Team 32
- Per GPU
- 32GB
- Total GPU memory
- 32GB
- GPU count
- 1
Meets the lower memory screen, but not the recommended working allowance.
Available GPU memory clears the lower 24GB VRAM with documented CPU offload settings screen but not the 80GB or more to remove the documented offload options working allowance. It may load, but choose a larger system when context, batch, concurrency or response time matter.
sme workstation
Company 64
- Per GPU
- 32GB
- Total GPU memory
- 64GB
- GPU count
- 2
Meets the lower memory screen, but not the recommended working allowance.
Available GPU memory clears the lower 24GB VRAM with documented CPU offload settings screen but not the 80GB or more to remove the documented offload options working allowance. It may load, but choose a larger system when context, batch, concurrency or response time matter.
sme workstation
Studio 96
- Per GPU
- 96GB
- Total GPU memory
- 96GB
- GPU count
- 1
Also meets this model page's recommended working allowance.
Available GPU memory exceeds the model developer's published requirement. Confirm speed, context, batch size and concurrent users before purchase.
sme workstation
Studio 192
- Per GPU
- 96GB
- Total GPU memory
- 192GB
- GPU count
- 2
Also meets this model page's recommended working allowance.
Available GPU memory exceeds the model developer's published requirement. Confirm speed, context, batch size and concurrent users before purchase.
pcie rack
Value Rack 128
- Per GPU
- 32GB
- Total GPU memory
- 128GB
- GPU count
- 4
Meets the lower memory screen, but not the recommended working allowance.
Available GPU memory clears the lower 24GB VRAM with documented CPU offload settings screen but not the 80GB or more to remove the documented offload options working allowance. It may load, but choose a larger system when context, batch, concurrency or response time matter.
pcie rack
Value Rack 256
- Per GPU
- 32GB
- Total GPU memory
- 256GB
- GPU count
- 8
Meets the lower memory screen, but not the recommended working allowance.
Available GPU memory clears the lower 24GB VRAM with documented CPU offload settings screen but not the 80GB or more to remove the documented offload options working allowance. It may load, but choose a larger system when context, batch, concurrency or response time matter.
pcie rack
Enterprise 384
- Per GPU
- 96GB
- Total GPU memory
- 384GB
- GPU count
- 4
Also meets this model page's recommended working allowance.
Available GPU memory exceeds the model developer's published requirement. Confirm speed, context, batch size and concurrent users before purchase.
pcie rack
Enterprise 768
- Per GPU
- 96GB
- Total GPU memory
- 768GB
- GPU count
- 8
Also meets this model page's recommended working allowance.
Available GPU memory exceeds the model developer's published requirement. Confirm speed, context, batch size and concurrent users before purchase.
pcie rack
H200 1.1TB
- Per GPU
- 141GB
- Total GPU memory
- 1,128GB
- GPU count
- 8
Also meets this model page's recommended working allowance.
Available GPU memory exceeds the model developer's published requirement. Confirm speed, context, batch size and concurrent users before purchase.
frontier partner
Frontier Native 2.3TB
- Per GPU
- 288GB
- Total GPU memory
- 2,304GB
- GPU count
- 8
Also meets this model page's recommended working allowance.
Available GPU memory exceeds the model developer's published requirement. Confirm speed, context, batch size and concurrent users before purchase.
frontier partner
Frontier Rack 20TB
- Per GPU
- 288GB
- Total GPU memory
- 20,736GB
- GPU count
- 72
Also meets this model page's recommended working allowance.
Available GPU memory exceeds the model developer's published requirement. Confirm speed, context, batch size and concurrent users before purchase.
Deployment reality
Strengths, limits and runtime route
What it is good at
- Official 24GB single-GPU route.
- Text-to-video and image-to-video in the same checkpoint.
- 720p generation at 1280 × 704 or portrait equivalent.
- Apache 2.0 licence and multi-GPU FSDP/Ulysses example.
Where to be cautious
- The 24GB route relies on CPU offload and conversion, which reduces speed.
- The official model card does not make a universal latency promise.
- Video quality depends on prompt, seed, frames, resolution and review criteria.
- Large storage and review workflows can dominate the system around the model.
Serving software
- Wan2.2 reference code
- Diffusers
- ComfyUI after workflow review
Before installation
- For Team 32, retain the documented offload, dtype conversion and CPU text-encoder settings.
- For Studio 96, test the no-offload route and compare latency and peak VRAM.
- Record 720p dimensions, frame count, steps, batch, latency and output size.
- Use representative motion, camera and subject prompts in acceptance.
System requirements
- GPU layout
- The minimum can fit on one GPU; multiple GPUs may still be useful for replicas or throughput.
- Context and cache
- The model context ceiling is not a guaranteed serving target. KV cache, batch size and concurrent sessions need separate capacity tests.
- System RAM
- Size system memory for model loading, runtime overhead, preprocessing and any CPU offload used by the final configuration.
- Storage
- Allow space for the pinned checkpoint, runtime images, caches, logs and at least one rollback version.
- Serving software
- Validate the exact checkpoint with Wan2.2 reference code, Diffusers, ComfyUI after workflow review before acceptance.
- Representative workload
- Benchmark representative prompts or media at the required context, quality, latency and concurrency.
Performance: speed, usable context and concurrency depend on the selected system, software and workload. No benchmark is quoted on this page.
Commercial and legal boundary
Apache License 2.0
Commercial use: permitted
The official model card states Apache 2.0 and places responsibility for lawful use on the operator.
Always retain the applicable notices and recheck the live terms for the intended organisation, territory, use and distribution route. Obtain legal advice where required; the official licence governs use.
Read the official licenceTechnical questions
Wan2.2 TI2V 5B deployment FAQ
Can Team 32 generate 720p Wan2.2 video?
It clears Wan's 24GB minimum and should use the documented offload route. Generation time and quality still need testing.
Why use a 96GB GPU?
Wan states that 80GB or more can remove several offload options, which may improve speed and simplify the execution path.
What must a video benchmark record?
Model revision, prompt, resolution, frames, duration, steps, batch, latency, peak VRAM and output review.
What a complete Wan2.2 TI2V 5B deployment needs
GPU memory is only one part of the system. Storage, data access, serving software, monitoring and administrator handover also affect a reliable deployment.
