TokenAssemble

Can an NVIDIA GeForce RTX 3090 run Qwen2.5-14B-Instruct?

Yes. Qwen2.5-14B-Instruct needs 17.8GB at Q8_0 with llama.cpp and 8K context; the NVIDIA GeForce RTX 3090 has 24GB of VRAM (23.5GB usable) — grade B, with decode speed in the interactive tier.

NVIDIA GeForce RTX 3090 · Qwen2.5-14B-Instruct · Q8_0

Fits — grade B

Interactive
weights 15.7 GBKV cache 1.61 GBoverhead 0.52 GBpool 23.5 GBneeds 17.8 GB

assumes llama.cpp · batch 1 · 8K context · fp16 KV cache

$1,499 MSRP · as of 2026-07-08

Affiliate link — we may earn a commission. Verdicts are computed before any link is attached.

Every quant, graded

NVIDIA GeForce RTX 3090 × Qwen2.5-14B-Instruct, llama.cpp, 8K context.

QuantFile sizeFitSpeed tier
Q8_015.7 GBFits · Binteractive
Q6_K12.1 GBFits · A+interactive
Q5_K_M10.5 GBFits · A+interactive
Q4_K_M9.0 GBFits · A+interactive

More models on the NVIDIA GeForce RTX 3090

Verdict computed from published specs and measured GGUF file sizes — see how the math works.