Can the DGX Spark (GB10) run OTel-2.0-LLM-31B-IT?

Yes. OTel-2.0-LLM-31B-IT fits the DGX Spark (GB10)'s 128 GB at Q4_K_M (about 20.8 GB needed), running at an estimated 8.3 tok/s. There's room for up to FP16 if you want higher quality.

VRAM
128 GB
Needs at Q4
20.8 GB
Headroom
107.2 GB
Speed (Q4_K_M)
~8.3 tok/s

Every quantization

OTel-2.0-LLM-31B-IT (32.1B) on 128 GB

QuantWeightsNeedsFitEst. speed
Q4_K_M19 GB20.8 GBFits easily~8.3 tok/s
Q5_K_M23 GB24.8 GBFits easily~6.8 tok/s
Q8_034 GB35.8 GBFits easily~4.6 tok/s
FP1664 GB65.8 GBFits easily~2.5 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.

Compare

Same model, other hardware - and other models on this card

OTel-2.0-LLM-31B-IT on other hardware

Also runs on the DGX Spark (GB10)

Frequently asked

Quick answers

Can the NVIDIA DGX Spark (GB10) run OTel-2.0-LLM-31B-IT?

Yes. OTel-2.0-LLM-31B-IT fits the DGX Spark (GB10)'s 128 GB at Q4_K_M (about 20.8 GB needed), running at an estimated 8.3 tok/s. There's room for up to FP16 if you want higher quality.

How much VRAM does OTel-2.0-LLM-31B-IT need?

About 19 GB of weights at Q4_K_M, 34 GB at Q8_0 and 64 GB at FP16. Add roughly 1.8 GB for the KV cache and runtime at modest context lengths.

How fast is OTel-2.0-LLM-31B-IT on the DGX Spark (GB10)?

Roughly 8.3 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.