Can NVIDIA DGX Spark (GB10) · 128 GB run LFM2.5 24B-A2B?

128 GB unified · 273 GB/s memory bandwidth · LFM2.5 24B-A2B has 24B parameters (2B active per token).

Short answer

Yes, excellent for chat and comfortable or better for every workload we test.

Best quantization for chat: Q4_K_M (14 GB of weights) on Ollama. Generation: 120–160 tok/s, leaving about 105 GB free for your other apps.

How it rates for each workload

Same model and machine, different jobs. Agents and long documents send far bigger prompts than chat, so they need much more speed and memory.

Workload	Verdict	Quant	Generation	First reply	Context
Chatwith Open WebUI	Excellent	Q4_K_M	120–160 tok/s	under 1 s	8K	Details
Coding questionswith Continue	Excellent	Q8_0	65–90 tok/s	≈1 s	16K	Details
Coding in a repositorywith Aider	Comfortable	Q8_0	60–80 tok/s	≈3 s	32K	Details
Agentic codingwith OpenCode	Comfortable	Q8_0	55–80 tok/s	≈4 s	32K	Details
Long documents (64K)with Open WebUI	Excellent	Q8_0	45–60 tok/s	≈10 s	64K	Details

Speeds are estimates calibrated against measured benchmarks on similar hardware. “First reply” is the time to read the workload’s opening prompt. How we calculate

Other models for NVIDIA DGX Spark (GB10) · 128 GB

The best-rated models for chat on this machine.

Everything NVIDIA DGX Spark (GB10) · 128 GB can run

Cheapest machines for LFM2.5 24B-A2B

Hardware rated comfortable or better for chat, lowest price first.

Same chip, other memory: 64 GB

Different tool, context size or workload?

These pages use typical settings. The full check models your exact setup.

Check my exact setup