What GPU do I need to run RedHatAI/DeepSeek-Coder-V2-Lite-Instruct-FP8?
15.7B parameters, published in F8_E4M3. View on Hugging Face
Set up DeepSeek-Co…ite-Instruct-FP8DeepSeek-Coder-V2-Lite-Instruct-FP8 is published by RedHatAI on Hugging Face, with 145,089 downloads and 14 likes to date. It's a DeepseekV2ForCausalLM model built for text-generation, published natively in F8_E4M3.
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 DeepSeek-Coder-V2-Lite-Instruct-FP8 at its published (F8_E4M3) precision: 1× RTX 4000 SFF Ada on runpod, at $0.180/hr per GPU ($0.180/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
DeepSeek-Coder-V2-Lite-Instruct-FP8: common questions
Does DeepSeek-Coder-V2-Lite-Instruct-FP8 fit on a 24 GB GPU?
Yes. At FP8 (native) it needs 17.6 GB of VRAM, so a 24 GB card holds it with 6.4 GB to spare. A 16 GB card is not enough for it at FP8 (native).
Is DeepSeek-Coder-V2-Lite-Instruct-FP8 already quantized?
Yes. It is published in FP8, one byte per parameter, so the 17.6 GB figure is already a quantized footprint rather than a full-precision one. Only INT4 goes below it, at 8.8 GB. A GPU without FP8 tensor cores cannot run it as published, which is why cards here are matched on precision support and not on VRAM alone.
What is the least VRAM DeepSeek-Coder-V2-Lite-Instruct-FP8 can run in?
8.8 GB, at INT4 (quantized), which fits a 12 GB card, against 17.6 GB at FP8 (native). 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 DeepSeek-Coder-V2-Lite-Instruct-FP8 lower the GPU bill?
Yes. At FP8 (native) the cheapest live fit is one RTX 4000 SFF Ada on runpod at $0.180/hr. At INT4 (quantized) it drops to one RTX 3060 on simplepod at $0.080/hr, provided a quantized checkpoint exists for it.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More RedHatAI models
- gemma-4-31B-it-FP8-block (31.3B, F8_E4M3)
- gemma-4-26B-A4B-it-FP8-dynamic (26.5B, F8_E4M3)
- gemma-4-12B-it-FP8-Dynamic (13.0B, F8_E4M3)
- Llama-3.2-1B-Instruct-FP8-dynamic (1.5B, F8_E4M3)
- Qwen3.5-9B-FP8-dynamic (9.4B, F8_E4M3)
- gemma-4-31B-it-FP8-dynamic (31.3B, F8_E4M3)
