Can an NVIDIA DGX Spark run Llama-3.2-1B-Instruct?
Yes. Llama-3.2-1B-Instruct needs 2.01GB at Q8_0 with llama.cpp and 8K context; the NVIDIA DGX Spark has 128GB of unified memory (~90% GPU-addressable) (114.7GB usable) — grade A+, with decode speed in the interactive tier.
NVIDIA DGX Spark · Llama-3.2-1B-Instruct · Q8_0
✅ Fits — grade A+
InteractivebetaNew hardware class — tier not yet calibrated
weights 1.32 GBKV cache 0.27 GBoverhead 0.42 GBpool 114.7 GBneeds 2.01 GB
assumes llama.cpp · batch 1 · 8K context · fp16 KV cache
$4,699 MSRP · as of 2026-07-11
Affiliate link — we may earn a commission. Verdicts are computed before any link is attached.
Every quant, graded
NVIDIA DGX Spark × Llama-3.2-1B-Instruct, llama.cpp, 8K context.
| Quant | File size | Fit | Speed tier |
|---|---|---|---|
| Q8_0 | 1.3 GB | Fits · A+ | interactive · beta |
| Q6_K | 1.0 GB | Fits · A+ | interactive · beta |
| Q5_K_M | 0.9 GB | Fits · A+ | interactive · beta |
| Q4_K_M | 0.8 GB | Fits · A+ | interactive · beta |
Llama-3.2-1B-Instruct on similar hardware
Verdict computed from published specs and measured GGUF file sizes — see how the math works.