Rent a GPU

Can the NVIDIA RTX 3090 Ti run Qwen2.5 Coder 14B?

RTX 3090 Ti × Qwen2.5 Coder 14B8K context
YesRuns fully on the GPU
Memory at Q8_017.9 GB of 24 GB
Weights 15.7 GBKV cache 1.6 GBRuntime 0.6 GB
QuantQ8_0Near-lossless
Speed~38tokens per second
Max context32Kthe model's full window
  1. FP16
  2. Q8_0
  3. Q6_K
  4. Q5_K_M
  5. Q4_K_M
  6. Q3_K_M
  7. Q2_K

Yes. The NVIDIA RTX 3090 Ti can run Qwen2.5 Coder 14B fully in VRAM at Q8_0 (near-lossless), using about 17.9 GB of the 24 GB available, at roughly 38 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts Qwen2.5 Coder 14B:

ollama run qwen2.5-coder:14b

Ollama's default download is Q4_K_M (about 11.2 GB here). You have room for Q8_0, which is near-lossless: pick that GGUF in LM Studio or from Hugging Face.

New to this? Step-by-step setup for the RTX 3090 Ti

Run it in the cloud

No NVIDIA RTX 3090 Ti? Run Qwen2.5 Coder 14B in the cloud.

Rent a cloud GPU by the hour. No upfront cost, stop any time.

Rent a GPU on RunPodRent a GPU on Vast.ai

Memory needed by quantization

At 8,192 tokens of context. The black line marks the 24 GB the NVIDIA RTX 3090 Ti can use.

QuantQualityMemoryFits?Speed
FP16Full quality31.8 GBToo big—
Q8_0Near-lossless17.9 GBFits~38 tok/s
Q6_KExcellent14.3 GBFits~50 tok/s
Q5_K_MVery good12.7 GBFits~57 tok/s
Q4_K_MGood, most popular11.2 GBFits~67 tok/s
Q3_K_MNoticeably degraded9.4 GBFits~84 tok/s
Q2_KHeavily degraded7.8 GBFits~109 tok/s

Measured speed from real RTX 3090 Ti owners

Tokens per second that people measured on their own NVIDIA RTX 3090 Ti, next to our estimate.

No one has measured Qwen2.5 Coder 14B on the NVIDIA RTX 3090 Ti yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an RTX 3090 Ti? Add your real speed

One command times Qwen2.5 Coder 14B in your own Ollama, shows you exactly what it would send, and asks before sending anything. No sign-up, no personal data.

macOS and Linux

curl -fsSL https://gpufit.dev/bench.sh | sh -s -- qwen2.5-coder:14b

Windows (PowerShell)

$env:GPUFIT_MODEL="qwen2.5-coder:14b"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run Qwen2.5 Coder 14B comfortably

Models that run well on the NVIDIA RTX 3090 Ti

Frequently asked questions

Can NVIDIA RTX 3090 Ti run Qwen2.5 Coder 14B?

Yes. The NVIDIA RTX 3090 Ti can run Qwen2.5 Coder 14B fully in VRAM at Q8_0 (near-lossless), using about 17.9 GB of the 24 GB available, at roughly 38 tokens/second.

How much VRAM does Qwen2.5 Coder 14B need?

About 11.2 GB at Q4_K_M with 8,192 tokens of context, and about 31.8 GB at full FP16 precision.

How fast is Qwen2.5 Coder 14B on the NVIDIA RTX 3090 Ti?

Roughly 38 tokens per second at Q8_0, estimated from the NVIDIA RTX 3090 Ti's 1008 GB/s memory bandwidth.