What GPU do I need to run numind/NuExtract-tiny?

464M parameters, published in F32. View on Hugging Face

464M
Parameters
F32
Native precision
Qwen2ForCausalLM
Architecture
text-generation
Pipeline

NuExtract-tiny is published by numind on Hugging Face, with 16,090 downloads and 45 likes to date. It's a Qwen2ForCausalLM 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.

PrecisionWeight sizeRequired VRAMCheapest live fitGPUs neededEst. $/hr (full fit)
FP321.7 GB2.1 GBRTX 30701$0.088/hr
FP8 (quantized)0.4 GB0.5 GBRTX 5060 Ti1$0.180/hr
INT4 (quantized)0.2 GB0.3 GBRTX 30701$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 NuExtract-tiny at its published (F32) precision: 1× RTX 3070, at $0.088/hr per GPU ($0.088/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.

NuExtract-tiny: 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: 98,304 bytes at 16-bit.

ContextKV cache, one sequence
4K0.38 GB
32K3.0 GB

Computed from the layer, head and window counts in the model's own configuration (numind/NuExtract-tiny), at 16 bits per cached value. Each concurrent sequence needs its own cache, on top of the weights.

NuExtract-tiny: common questions

How much VRAM does NuExtract-tiny need?

2.1 GB at FP32, 0.5 GB at FP8 (quantized), 0.3 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 1.7 GB of weights plus inference overhead is the whole requirement.

Can NuExtract-tiny run in 16-bit instead of FP32?

Yes. Its published weights are FP32, 1.7 GB, or 2.1 GB once inference overhead is added. Loading the same weights in 16 bits halves that to 0.9 GB, or 1.0 GB with overhead. How much accuracy the cast costs is model-specific and is not measured here.

How many copies of NuExtract-tiny fit on one RTX 3070?

3, by VRAM alone. That card carries 8.0 GB and one copy needs 2.1 GB at FP32, on a live rate of $0.088/hr for the whole card. Throughput is not modelled here, so 3 copies is not 3 times the requests served.

Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.

More Qwen1.5 models

All 18 Qwen1.5 models: VRAM and GPU requirements

Lineage

Based on Qwen1.5-0.5B.

Alternatives at this size

Other models for text-generation within about a third of NuExtract-tiny's 464M parameters, from other model lines.

More on NuExtract-tiny

Related reading: RTX 3070 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

Connect your accounts

One console for the GPU clouds you already use.

Connect your accounts for $20 a month, flat. Your provider bills the GPU.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.