What GPU do I need to run Vamsi/T5_Paraphrase_Paws?
223M parameters, published in F32. View on Hugging Face
T5_Paraphrase_Paws is published by Vamsi on Hugging Face, with 79,913 downloads and 44 likes to date. It's a T5ForConditionalGeneration model built for text-generation, published natively in F32.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision times a flat 1.2 overhead for activations and fragmentation. The KV-cache grows with context and is not in that factor; it is listed per model below where the architecture is published. Full formula and assumptions: methodology.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| FP32 | 0.8 GB | 1.0 GB | Quadro M4000 | 1 | $0.046/hr |
| FP8 (quantized) | 0.2 GB | 0.2 GB | RTX 5060 Ti | 1 | $0.180/hr |
| INT4 (quantized) | 0.1 GB | 0.1 GB | RTX 3070 | 1 | $0.088/hr |
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run T5_Paraphrase_Paws at its published (F32) precision: 1× Quadro M4000, at $0.046/hr per GPU ($0.046/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
T5_Paraphrase_Paws: KV cache by context length
The KV cache is the memory the attention layers hold for every token of context, on top of the weights. It is not part of the flat 1.2x overhead in the table above, grows with context length and with every concurrent request, and is why a long-context deployment needs more VRAM than the table shows.
KV-cache size for T5_Paraphrase_Paws is not published for this architecture, so no figure is shown.
T5_Paraphrase_Paws: common questions
How much VRAM does T5_Paraphrase_Paws need?
1.0 GB at FP32, 0.2 GB at FP8 (quantized), 0.1 GB at INT4 (quantized). All of those sit under 6 GB, the smallest capacity this page reasons about, so VRAM is not what limits where this model runs. The 0.8 GB of weights plus inference overhead is the whole requirement.
Can T5_Paraphrase_Paws run in 16-bit instead of FP32?
Yes. Its published weights are FP32, 0.8 GB, or 1.0 GB once inference overhead is added. Loading the same weights in 16 bits halves that to 0.4 GB, or 0.5 GB with overhead. How much accuracy the cast costs is model-specific and is not measured here.
How many copies of T5_Paraphrase_Paws fit on one Quadro M4000?
8, by VRAM alone. That card carries 8.0 GB and one copy needs 1.0 GB at FP32, on a live rate of $0.046/hr for the whole card. Throughput is not modelled here, so 8 copies is not 8 times the requests served.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More T5 models
- chatgpt_paraphraser_on_T5_base (223M, F32)
- t5-3b (2.9B, F32)
Alternatives at this size
Other models for text-generation within about a third of T5_Paraphrase_Paws's 223M parameters, from other model lines.
- pythia-160m (213M, F16)
- gemma-3-270m (268M, BF16)
- gpt-neo-125m (150M, F32)
- llm-jp-3-150m (152M, BF16)
- progen2-small (151M, F32)
More on T5_Paraphrase_Paws
Fits on an 8 GB GPU at FP32: every model that fits in 8 GB.
Related reading: H100 pricing and specs, How much VRAM you need for LLMs, Serving LLMs with vLLM, vLLM vs TensorRT-LLM vs SGLang, Best GPU for LLM inference, and What AI model fine-tuning is.
Your own GPU cloud accounts
One console for the GPU clouds you already rent from. Your keys stay on your machine.
$20 a month, flat