Can the DGX Spark (GB10) run Qwen2.5-Coder-14B-Instruct?
Yes. Qwen2.5-Coder-14B-Instruct fits the DGX Spark (GB10)'s 128 GB at Q4_K_M (about 10.8 GB needed), running at an estimated 17 tok/s. There's room for up to FP16 if you want higher quality.
Every quantization
Qwen2.5-Coder-14B-Instruct (14.8B) on 128 GB
| Quant | Weights | Needs | Fit | Est. speed |
|---|---|---|---|---|
| Q4_K_M | 9 GB | 10.8 GB | Fits easily | ~17 tok/s |
| Q5_K_M | 11 GB | 12.8 GB | Fits easily | ~14 tok/s |
| Q8_0 | 16 GB | 17.8 GB | Fits easily | ~9.8 tok/s |
| FP16 | 30 GB | 31.8 GB | Fits easily | ~5.2 tok/s |
Estimates. Needs = weights + 1.8 GB for KV cache and runtime at modest context. Speed is single-stream decode scaled from the DGX Spark (GB10)'s 273.2 GB/s bandwidth (Estimated from memory bandwidth (llama.cpp decode)). Long contexts need more memory and run slower.
Run it
Copy, paste, go
llama-server -hf Qwen/Qwen2.5-Coder-14B-Instruct-GGUF -ngl 99Ollama pulls a Q4 build by default. Pick a larger quant only if the table above says it fits. Full Qwen2.5-Coder-14B-Instruct details →
Compare
Same model, other hardware - and other models on this card
Qwen2.5-Coder-14B-Instruct on other hardware
- RTX 5090~114 tok/s
- RTX 5090 D~114 tok/s
- RTX 6000D~100 tok/s
- RTX 4090~70 tok/s
- RTX 3090~61 tok/s
- Radeon RX 7900 XTX~61 tok/s
- RTX 5080~61 tok/s
- RTX 3080 Ti~58 tok/s
Also runs on the DGX Spark (GB10)
- gpt-oss-120b~35 tok/s
- Qwen2.5 72B~3.9 tok/s
- Llama 3.3 70B~3.9 tok/s
- Qwen3.6 35B A3B~60 tok/s
- Qwen3.5 35B A3B~60 tok/s
- dolphin-2.9.1-yi-1.5-34b~7.8 tok/s
- Gemma 4 31B~8.3 tok/s
- Qwen3 32B~8.3 tok/s
Frequently asked
Quick answers
Can the NVIDIA DGX Spark (GB10) run Qwen2.5-Coder-14B-Instruct?
Yes. Qwen2.5-Coder-14B-Instruct fits the DGX Spark (GB10)'s 128 GB at Q4_K_M (about 10.8 GB needed), running at an estimated 17 tok/s. There's room for up to FP16 if you want higher quality.
How much VRAM does Qwen2.5-Coder-14B-Instruct need?
About 9 GB of weights at Q4_K_M, 16 GB at Q8_0 and 30 GB at FP16. Add roughly 1.8 GB for the KV cache and runtime at modest context lengths.
How fast is Qwen2.5-Coder-14B-Instruct on the DGX Spark (GB10)?
Roughly 17 tokens per second at Q4_K_M (single user, llama.cpp-style decode). This is an estimate from the DGX Spark (GB10)'s 273.2 GB/s memory bandwidth.