What GPU do I need to run openai-community/openai-gpt?
120M parameters, published in F32. View on Hugging Face
Set up openai-gptopenai-gpt is published by openai-community on Hugging Face, with 185,184 downloads and 304 likes to date. It's a OpenAIGPTLMHeadModel 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 | 0.4 GB | 0.5 GB | Quadro M4000 | 1 | $0.058/hr |
| FP8 (quantized) | 0.1 GB | 0.1 GB | RTX 4000 SFF Ada | 1 | $0.198/hr |
| INT4 (quantized) | 0.1 GB | 0.1 GB | RTX 3060 | 1 | $0.110/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 openai-gpt at its published (F32) precision: 1× Quadro M4000, at $0.058/hr per GPU ($0.058/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
openai-gpt: 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.
Multi-head attention: every layer caches keys and values for every head. Cached per token: 36,864 bytes at 16-bit.
| Context | KV cache, one sequence |
|---|---|
| 512 (model maximum) | 0.02 GB |
Computed from the layer, head and window counts in the model's own configuration (openai-community/openai-gpt), at 16 bits per cached value. Each concurrent sequence needs its own cache, on top of the weights.
openai-gpt: common questions
How much VRAM does openai-gpt need?
0.5 GB at FP32, 0.1 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 0.4 GB of weights plus inference overhead is the whole requirement.
Can openai-gpt run in 16-bit instead of FP32?
Yes. Its published weights are FP32, 0.4 GB, or 0.5 GB once inference overhead is added. Loading the same weights in 16 bits halves that to 0.2 GB, or 0.3 GB with overhead. How much accuracy the cast costs is model-specific and is not measured here.
How many copies of openai-gpt fit on one Quadro M4000?
14, by VRAM alone. That card carries 8.0 GB and one copy needs 0.5 GB at FP32, on a live rate of $0.058/hr for the whole card. Throughput is not modelled here, so 14 copies is not 14 times the requests served.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
Alternatives at this size
Other models for text-generation within about a third of openai-gpt's 120M parameters, from other model lines.
- gpt2 (137M, F32)
- SmolLM2-135M (135M, BF16)
- macbert4csc-base-chinese (102M, F32)
- gpt-neo-125m (150M, F32)
- mamba-130m-hf (129M, F32)
More on openai-gpt
Fits on an 8 GB GPU at FP32: every model that fits in 8 GB.
Best chat and assistants models: how openai-gpt ranks against the rest.
Related reading: H100 pricing and specs, How much VRAM you need for LLMs, Serving LLMs with vLLM, vLLM vs TensorRT-LLM vs SGLang, and Best GPU for LLM inference.
