FreeLLMGPUs › Mini PC
Best free AI models for the NVIDIA DGX Spark 128 GB
NVIDIA DGX Spark 128 GB: 128 GB of shared memory (about 96 GB usable by the GPU), 273 GB/s. These are the free models it runs, ranked by Arena votes, with the speed you can expect.
Simulate your setup · Check the price on Amazon ↗ · Compare all GPUs
Voted models that fit fully on the GPU
| Model | Arena score | Size | 4-bit file | Tokens/s |
|---|---|---|---|---|
| Gemma 4 31B |
1443 | 31.3 B | 20 GB | 10.0 |
| Qwen3.8-27B alibaba |
1441 | 27.8 B | 18 GB | 12 |
| Gemma 4 26B A4B google · MoE, 4 B active |
1434 | 25.8 B | 17 GB | 60 |
| Qwen3.5-122B-A10B alibaba · MoE, 10 B active |
1417 | 125.1 B | 77 GB | 31 |
| Qwen3.5-27B alibaba |
1409 | 27.8 B | 18 GB | 12 |
| glm-4.6v zai · MoE, 14.3 B active |
1376 | 107.7 B | 66 GB | 20 |
| gemma-3-27b-it |
1358 | 27.4 B | 18 GB | 12 |
| glm-4.5v zai · MoE, 14.3 B active |
1333 | 107.7 B | 66 GB | 20 |
Popular small models
Official small models with no Arena votes yet, ordered by downloads on Hugging Face (popularity, not quality).
| Model | Downloads/month | Size | 4-bit file | Tokens/s |
|---|---|---|---|---|
| Qwen3-0.6B Qwen |
29.5M | 0.8 B | 1.7 GB | 130 |
| Qwen3-4B Qwen |
11.8M | 4 B | 3.6 GB | 55 |
| Qwen3-8B Qwen |
8.9M | 8.2 B | 6.2 GB | 33 |
| Qwen3-14B Qwen |
8.4M | 14.8 B | 10 GB | 20 |
| Qwen3.5-4B Qwen |
7.8M | 4.7 B | 4.0 GB | 64 |
| Qwen3.5-9B Qwen |
7.5M | 9.7 B | 7.1 GB | 33 |
Estimates at 4-bit (Q4_K_M) with an 8K context, calibrated on 44 real llama.cpp tests (typical error about ±10%). Tokens per second: about 10 is reading speed. As an Amazon Associate, FreeLLMArena earns from qualifying purchases; the links do not change the rankings.
Questions
What is the best free AI model for the NVIDIA DGX Spark 128 GB?
Gemma 4 31B (Arena score 1443) is the highest-voted open model that fits entirely in the ~96 GB of shared memory the GPU can use at 4-bit, writing about 10.0 tokens per second.
How big a model can the NVIDIA DGX Spark 128 GB run?
About 148 billion parameters for a dense model at 4-bit with an 8K context, fully on the GPU. Mixture-of-experts models can be bigger, and with 64 GB of system RAM larger models still run, more slowly.
Is the NVIDIA DGX Spark 128 GB good for local LLMs?
It has 128 GB of memory and 273 GB/s of bandwidth. Memory decides which models fit; bandwidth decides how fast they write. With 24 GB or more it runs 27–32 B models, the sweet spot of quality for home use.
Similar cards
- Mac M4 Max 128 GB 128 GB · 546 GB/s
- Ryzen AI Max+ 395 128 GB 128 GB · 256 GB/s
- H200 141 GB · 4800 GB/s
- RTX PRO 6000 Blackwell 96 GB · 1792 GB/s
- H100 SXM 80 GB · 3350 GB/s
- A100 80 GB 80 GB · 2039 GB/s