How much VRAM does deepseek-r1-14b need?

Q4_K_M is exactly 8,988,109,888 bytes (8.37 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

deepseek-ai · text

deepseek-r1-14b

deepseek-ai/deepseek-r1-14b

deepseek-r1-14b at Q4_K_M is exactly 8,988,109,888 bytes (8.37 GiB / 8.99 GB) — an effective 4.868 bits per weight, not the nominal 4.

From the file· summed from 1 file(s)

Parameters

14.8B

Architecture

qwen2

Context

—

native (config.json)

License

apache-2.0

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
Q4_K_M	8.37 GiB	8,988,109,888	4.868	—	ValueFX9507
IQ4_NL2 shards	16.02 GiB	17,204,533,376	9.319	—	ValueFX9507

Compare with

same modality, comparable size

vs Qwen3-Coder-30B-A3B-Instruct vs Qwen3.6-27B vs Qwen3.8-27B vs gemma-4-12B-it-qat-q4_0-unquantized vs gemma-4-E4B-it vs Qwen3-30B-A3B-Thinking-2507 All alternatives →Will it fit on my card? →

Why other calculators give a different number

A parameters × bits ÷ 8 estimate puts Q4_K_M at roughly 7.74 GiB. The real file is 8.37 GiB, because a quantization is a mixture and some tensors are always kept at higher precision.

Architecture

Architecture unavailable — this repository is gated and no ungated mirror was found. Exact file sizes above are still authoritative; only the KV math needs the config.

Questions people ask

How much VRAM does deepseek-r1-14b need?: Q4_K_M is exactly 8,988,109,888 bytes (8.37 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
Which quantization of deepseek-r1-14b should I use?: Q4_K_M is the usual default. Pick the largest quantization that fits your card at the context you actually need — the table above gives exact sizes for every one published.