What GPU do I need to run Vikhrmodels/Vikhr-Nemo-12B-Instruct-R-21-09-24?
12.2B parameters, published in BF16. View on Hugging Face
Set up Vikhr-Nemo-…truct-R-21-09-24Vikhr-Nemo-12B-Instruct-R-21-09-24 is published by Vikhrmodels on Hugging Face, with 56,513 downloads and 141 likes to date. It's a MistralForCausalLM model built for text-generation, published natively in BF16.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for KV-cache, activations, and fragmentation. Full formula and assumptions: methodology.
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 Vikhr-Nemo-12B-Instruct-R-21-09-24 at its published (BF16) precision: 1× RTX A6000 on runpod, at $0.330/hr per GPU ($0.330/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Vikhr-Nemo-12B-Instruct-R-21-09-24: common questions
Does Vikhr-Nemo-12B-Instruct-R-21-09-24 fit on a 32 GB GPU?
Yes. At BF16 it needs 27.4 GB of VRAM, so a 32 GB card holds it with 4.6 GB to spare. A 24 GB card is not enough for it at BF16.
What is the least VRAM Vikhr-Nemo-12B-Instruct-R-21-09-24 can run in?
6.8 GB, at INT4 (quantized), which fits an 8 GB card, against 27.4 GB at BF16. That row assumes an INT4 checkpoint has actually been published for this model, so check its Hugging Face page before planning around it.
Does quantizing Vikhr-Nemo-12B-Instruct-R-21-09-24 lower the GPU bill?
Yes. At BF16 the cheapest live fit is one RTX A6000 on runpod at $0.330/hr. At INT4 (quantized) it drops to one RTX 3070 on simplepod at $0.050/hr, provided a quantized checkpoint exists for it.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More Vikhrmodels models
- bert-base-uncased (110M, F32)
- Qwen3-0.6B (752M, BF16)
- gpt2 (137M, F32)
- Qwen3-8B (8.2B, BF16)
- Qwen3.6-35B-A3B-FP8 (36.0B, F8_E4M3)
- Qwen3.5-9B (9.7B, BF16)
