Rent a GPU

Can the NVIDIA RTX 5070 Ti run Qwen2.5 32B?

RTX 5070 Ti × Qwen2.5 32B8K context
Yes, with heavy quantizationFits only at a low-quality quant
Memory at Q2_K15 GB of 16 GB
Weights 12.3 GBKV cache 2.1 GBRuntime 0.6 GB
QuantQ2_KHeavily degraded
Memory15 GBof 16 GB usable
Speed~44tokens per second
  1. FP16
  2. Q8_0
  3. Q6_K
  4. Q5_K_M
  5. Q4_K_M
  6. Q3_K_M
  7. Q2_K

Only just. Qwen2.5 32B fits on the NVIDIA RTX 5070 Ti at Q2_K, which costs noticeable quality. Expect about 44 tokens/second. A card with more memory is a better experience.

Try other context lengths

Run it with Ollama

Ollama's default qwen2.5:32b download is Q4_K_M, which needs about 22.6 GB, more than the 16 GB available. Download the Q2_K GGUF instead (LM Studio lists quants per model), or try a smaller context length.

Run it in the cloud

Want full quality? Run Qwen2.5 32B on a bigger rented GPU.

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 16 GB the NVIDIA RTX 5070 Ti can use.

QuantQualityMemoryFits?Speed
FP16Full quality68.3 GBToo big—
Q8_0Near-lossless37.6 GBToo big—
Q6_KExcellent29.6 GBToo big—
Q5_K_MVery good26.1 GBToo big—
Q4_K_MGood, most popular22.6 GBToo big—
Q3_K_MNoticeably degraded18.8 GBToo big—
Q2_KHeavily degraded15 GBFits~44 tok/s

GPUs that run Qwen2.5 32B comfortably

Check NVIDIA RTX 3090 prices

Models that run well on the NVIDIA RTX 5070 Ti

Frequently asked questions

Can NVIDIA RTX 5070 Ti run Qwen2.5 32B?

Only just. Qwen2.5 32B fits on the NVIDIA RTX 5070 Ti at Q2_K, which costs noticeable quality. Expect about 44 tokens/second. A card with more memory is a better experience.

How much VRAM does Qwen2.5 32B need?

About 22.6 GB at Q4_K_M with 8,192 tokens of context, and about 68.3 GB at full FP16 precision.

How fast is Qwen2.5 32B on the NVIDIA RTX 5070 Ti?

Roughly 44 tokens per second at Q2_K, estimated from the NVIDIA RTX 5070 Ti's 896 GB/s memory bandwidth.