text model · Qwen2.5-VL · Linux
Can I run Qwen2.5-VL 3B on Nvidia DGX Spark (128GB)?
Yes. Qwen2.5-VL 3B runs on Nvidia DGX Spark (128GB) at Q4_K_M (~4.4 GB of ~112 GB usable).
Runs at Q4_K_M using ~4.4 GB of ~112 GB usable. You have room for FP16 for higher quality.
That figure is at a 4k context and moves about ±15% as context length changes. Nvidia DGX Spark (128GB) leaves ~107.6 GB of headroom, room to step up to FP16 for higher quality.
- Q4_K_M needed
- ~4.4 GB
- Usable on device
- ~112 GB
- Device memory
- 128 GB
- Best quant
- Q4_K_M
Which quant fits
Running cost · estimate
- Power draw
- ~140 W
- Electricity / 1M tokens
- ~$0.1
- Pays for itself after
- ~9,998M tok
At ~$0.15/kWh and the estimated ~58 tok/s, a million generated tokens costs about $0.1 in electricity. Versus a hosted API at ~$0.5 per million tokens, the ~$3,999 Nvidia DGX Spark (128GB) pays for itself after roughly 9,998 million tokens, so local hardware is mostly a fixed cost, not a per-token one. TDP is the peak draw, so this is an upper bound. Assumptions.
Run it
Pick your tool. All 2 load the same Q4_K_M weights.
llama-cli -hf ggml-org/Qwen2.5-VL-3B-Instruct-GGUF:Q4_K_M lms get ggml-org/Qwen2.5-VL-3B-Instruct-GGUF How to run it
On Linux use Ollama (One-line install, simple single-user UX.).
- Parameters
- 3.75B
- Q4_K_M size
- 3.05 GB
- Q8_0 size
- 4.31 GB
- Context
- 32k
- Memory
- 128 GB unified
- Usable for weights
- ~112 GB
- Power draw
- ~140 W
- Best runtime
- llama.cpp (CUDA) / Ollama (CUDA)
You could also run
Run Qwen2.5-VL 3B on other hardware
FAQ
Can Nvidia DGX Spark (128GB) run Qwen2.5-VL 3B?
Yes. Qwen2.5-VL 3B runs on Nvidia DGX Spark (128GB) at Q4_K_M (~4.4 GB of ~112 GB usable).
How much memory does Qwen2.5-VL 3B need?
Nvidia DGX Spark (128GB) has room to spare. At Q4_K_M the weights are ~3.05 GB; with KV cache and runtime overhead, budget ~4.4 GB at a 4k context.
What is the best tool to run Qwen2.5-VL 3B on Linux?
Ollama for a simple setup; vLLM for the most speed. vLLM shines for multi-user serving/throughput. For a single local chat, Ollama or llama.cpp is simpler and lighter.
Embed this
A live badge for your model card or README, updated as the data is. [](https://localmodel.run/can-i-run/qwen2.5-vl-3b/nvidia-dgx-spark-128gb) Sources
-
docs.nvidia.com · 2 sources
-
github.com · 1 source
-
huggingface.co · 2 sources
-
nvidia.com · 1 source
-
nvidianews.nvidia.com · 1 source
-
ollama.com · 1 source
-
tomshardware.com · 1 source
Weights are measured from GGUF files; KV cache and overhead are computed, so totals can vary ~15% with context and runtime. Any tok/s is a bandwidth estimate. See methodology.