Can the DGX Spark (GB10) run Ling 3.0 Tiny?
Yes. Ling 3.0 Tiny fits the DGX Spark (GB10)'s 128 GB at Q4_K_M (about 6.8 GB needed), running at an estimated 31 tok/s. There's room for up to FP16 if you want higher quality.
Every quantization
Ling 3.0 Tiny (7.9B) on 128 GB
| Quant | Weights | Needs | Fit | Est. speed |
|---|---|---|---|---|
| Q4_K_M | 5 GB | 6.8 GB | Fits easily | ~31 tok/s |
| Q5_K_M | 6 GB | 7.8 GB | Fits easily | ~26 tok/s |
| Q8_0 | 8 GB | 9.8 GB | Fits easily | ~20 tok/s |
| FP16 | 16 GB | 17.8 GB | Fits easily | ~9.8 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 inclusionAI/Ling-3.0-tiny-GGUF -ngl 99Ollama pulls a Q4 build by default. Pick a larger quant only if the table above says it fits. Full Ling 3.0 Tiny details →
Compare
Same model, other hardware - and other models on this card
Ling 3.0 Tiny on other hardware
- RTX 5090~206 tok/s
- RTX 5090 D~205 tok/s
- RTX 6000D~180 tok/s
- RTX 4090~125 tok/s
- RTX 3090~110 tok/s
- Radeon RX 7900 XTX~110 tok/s
- RTX 5080~110 tok/s
- RTX 3080 Ti~105 tok/s
Also runs on the DGX Spark (GB10)
- gpt-oss-120b~35 tok/s
- Llama 3.3 70B~3.9 tok/s
- Nemotron 3.5 Super VL~4.1 tok/s
- Qwen3.6 35B A3B~60 tok/s
- Laguna-XS-2.1~8.3 tok/s
- Gemma 4 31B~8.3 tok/s
- Qwen3 32B~8.3 tok/s
- Qwen3-Coder-30B-A3B-Instruct~59 tok/s
Frequently asked
Quick answers
Can the NVIDIA DGX Spark (GB10) run Ling 3.0 Tiny?
Yes. Ling 3.0 Tiny fits the DGX Spark (GB10)'s 128 GB at Q4_K_M (about 6.8 GB needed), running at an estimated 31 tok/s. There's room for up to FP16 if you want higher quality.
How much VRAM does Ling 3.0 Tiny need?
About 5 GB of weights at Q4_K_M, 8 GB at Q8_0 and 16 GB at FP16. Add roughly 1.8 GB for the KV cache and runtime at modest context lengths.
How fast is Ling 3.0 Tiny on the DGX Spark (GB10)?
Roughly 31 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.