Skip to content

Can RTX 4090 run Qwen3 14B Instruct?

Comfortable: GGUF Q5_K_M needs 11.7 GB at 4K, batch 1; headroom 12.3 GB.

Text input, FP16 KV cache, one card. Unified-memory capacity uses the GPU guide’s usable limit; negative headroom may require host offload. Speed source settings may differ from this 4K estimate.

Measured runs

FrameworkQuanttok/sVRAM used (GB)
ExLlamaV2EXL2 4.65bpw11810

Quant memory at 4K

QuantTotal GBVerdictWeight sizing
GGUF Q4_K_M10.0ComfortableEstimated weights
GGUF Q5_K_M11.7ComfortableEstimated weights
AWQ INT48.4ComfortableEstimated weights
EXL2 4.65bpw9.7ComfortableEstimated weights

Context capacity · GGUF Q5_K_M

ContextTotal GBVerdict
4K11.7Comfortable
16K13.7Comfortable
32K16.5Comfortable

Generation speed

Measured: 118 tok/s, EXL2 4.65bpw, ExLlamaV2

GGUF Q5_K_M: 67–89 tok/s · Derived range

Other model / GPU pairs