T5 Recipe Generation — Hardware Requirements & GPU Compatibility
Chat
T5 Recipe Generation is a 223M-parameter open language model from flax-community. It supports a context window of up to 512 tokens. At BF16 it needs about 0.49 GB of VRAM — see which GPUs and Macs can run it below.
2.9K downloads
76 likesSpecifications
- Publisher
- flax-community
- Parameters
- 223M
- Architecture
- T5ForConditionalGeneration
- Context Length
- 512 tokens
- Vocabulary Size
- 32,128
- Release Date
- 2023-08-03
Get Started
HuggingFace
How Much VRAM Does T5 Recipe Generation Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 0.5 GB | — | 0.45 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run T5 Recipe Generation?
BF16 · 0.5 GBT5 Recipe Generation (BF16) requires 0.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ GB is recommended. 35 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run T5 Recipe Generation?
BF16 · 0.5 GB33 devices with unified memory can run T5 Recipe Generation, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does T5 Recipe Generation need?
T5 Recipe Generation requires 0.5 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 223M × 16 bits ÷ 8 = 0.4 GB
KV Cache + Overhead ≈ 0.1 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
BF160.5 GB- Can I run T5 Recipe Generation on a Mac?
T5 Recipe Generation requires at least 0.5 GB at BF16, 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 T5 Recipe Generation locally?
Yes — T5 Recipe Generation can run locally on consumer hardware. At BF16 quantization it needs 0.5 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is T5 Recipe Generation?
At BF16, T5 Recipe Generation can reach ~5949 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~1337 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 0.5 × 0.55 = ~5949 tok/s
Estimated speed at BF16 (0.5 GB)
~5949 tok/s~1337 tok/s~4447 tok/s~3678 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of T5 Recipe Generation?
At BF16, the download is about 0.45 GB.
- Which GPUs can run T5 Recipe Generation?
35 consumer GPUs can run T5 Recipe Generation at BF16 (0.5 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 35 GPUs have plenty of headroom for comfortable inference.
- Which devices can run T5 Recipe Generation?
33 devices with unified memory can run T5 Recipe Generation at BF16 (0.5 GB), including Mac Mini M4 (16 GB), Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.