Can the DGX Spark (GB10) run dolphin-2.9.1-yi-1.5-34b?
Yes. dolphin-2.9.1-yi-1.5-34b fits the DGX Spark (GB10)'s 128 GB at Q4_K_M (about 21.8 GB needed), running at an estimated 7.8 tok/s. There's room for up to FP16 if you want higher quality.
Every quantization
dolphin-2.9.1-yi-1.5-34b (34.4B) on 128 GB
| Quant | Weights | Needs | Fit | Est. speed |
|---|---|---|---|---|
| Q4_K_M | 20 GB | 21.8 GB | Fits easily | ~7.8 tok/s |
| Q5_K_M | 24 GB | 25.8 GB | Fits easily | ~6.5 tok/s |
| Q8_0 | 37 GB | 38.8 GB | Fits easily | ~4.2 tok/s |
| FP16 | 69 GB | 70.8 GB | Fits easily | ~2.3 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 mradermacher/dolphin-2.9.1-yi-1.5-34b-GGUF -ngl 99Ollama pulls a Q4 build by default. Pick a larger quant only if the table above says it fits. Full dolphin-2.9.1-yi-1.5-34b details →
Compare
Same model, other hardware - and other models on this card
dolphin-2.9.1-yi-1.5-34b on other hardware
- RTX 5090~51 tok/s
- RTX 5090 D~51 tok/s
- RTX 6000D~45 tok/s
- RTX 4090~31 tok/s
- Radeon RX 7900 XTX~28 tok/s
- RTX 3090~27 tok/s
- MacBook Pro 16" M4 Max~16 tok/s
- Arc Pro B60~13 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
- Gemma 4 31B~8.3 tok/s
- Qwen3 32B~8.3 tok/s
- GLM-4.7-Flash~60 tok/s
Frequently asked
Quick answers
Can the NVIDIA DGX Spark (GB10) run dolphin-2.9.1-yi-1.5-34b?
Yes. dolphin-2.9.1-yi-1.5-34b fits the DGX Spark (GB10)'s 128 GB at Q4_K_M (about 21.8 GB needed), running at an estimated 7.8 tok/s. There's room for up to FP16 if you want higher quality.
How much VRAM does dolphin-2.9.1-yi-1.5-34b need?
About 20 GB of weights at Q4_K_M, 37 GB at Q8_0 and 69 GB at FP16. Add roughly 1.8 GB for the KV cache and runtime at modest context lengths.
How fast is dolphin-2.9.1-yi-1.5-34b on the DGX Spark (GB10)?
Roughly 7.8 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.