Hardware · NVIDIA
What AI models can the NVIDIA GB10 (128 GB) run?
- Unified memory
- 128 GB
- Usable for models
- 115 GB
- Memory bandwidth
- 273 GB/s
- FP16 compute
- 31.0 TFLOPS
- Released
- 2025
macOS lets the GPU use roughly two-thirds to three-quarters of unified memory by default, so we plan around that figure rather than the full 128 GB.
More about this hardware
| Maker | NVIDIA |
|---|---|
| Type | Unified-memory system on a chip |
| GPU share of memory | 90% (what the GPU can typically be given for a model) |
| Chip | NVIDIA GB10 |
Apps that run models well on the NVIDIA GB10 (128 GB)
8 products with the NVIDIA GB10 (128 GB)
NVIDIA DGX SparkProduct page (opens in a new tab)
ASUS Ascent GX10Product page (opens in a new tab)
Dell Pro Max with GB10Product page (opens in a new tab)
HP ZGX Nano G1n AI StationProduct page (opens in a new tab)
Lenovo ThinkStation PGXProduct page (opens in a new tab)
MSI EdgeXpert MS-C931Product page (opens in a new tab)
GIGABYTE AI TOP ATOMGIGABYTE · Mini PC · 64 or 128 GB · $3,500Product page (opens in a new tab)
Acer Veriton GN100 AI Mini WorkstationProduct page (opens in a new tab)
Best LLMs for the NVIDIA GB10 (128 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 91Excellent quality (A+) · 91 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | Kolibri 1 (78B-A3.5B) | Q8_0 | 92.8 GB | 41.5 tok/s | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Coder Next (80B-A3B) | Q8_0 | 94.5 GB | 46.8 tok/s | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3-Next 80B-A3B Thinking | Q8_0 | 96.2 GB | 46.8 tok/s | Runs great |
| 84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | gpt-oss 120B | MXFP4 | 76.7 GB | 56.9 tok/s | Runs great |
| 84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Next 80B-A3B Instruct | Q8_0 | 96.2 GB | 46.8 tok/s | Runs great |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.5 122B-A10B | Q4_K_M | 86.3 GB | 30.1 tok/s | Runs great |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 122B-A10B | Q4_K_M | 86.3 GB | 30.1 tok/s | Runs great |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3.5 Super VL 120B-A12B | Q4_K_M | 85.8 GB | 25.5 tok/s | Runs well |
| 93Excellent quality (A+) · 93 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.6 35B-A3B | Q8_0 | 48.1 GB | 46.8 tok/s | Runs great |
| 93Excellent quality (A+) · 93 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 35B-A3B | Q8_0 | 48.1 GB | 46.8 tok/s | Runs great |
| 93Excellent quality (A+) · 93 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-V 4.7 35B-A3B | Q8_0 | 47.3 GB | 46.8 tok/s | Runs great |
| 81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | Laguna S 2.1 (118B-A8B) | Q4_K_M | 83.1 GB | 36.7 tok/s | Runs great |
Best Image models for the NVIDIA GB10 (128 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 91Excellent quality (A+) · 91 of 100: how capable the model is at FP8, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax H3 Image | FP8 | 72.0 GB | 19 s | Runs well |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | Krea 2 Turbo | FP16 | 37.4 GB | 9.0 s | Runs great |
| 84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 9B | FP16 | 37.1 GB | 3.8 s | Runs great |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | Cosmos3-Super Text2Image (64B) | FP8 | 69.1 GB | 75 s | Slow |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | Ming-Image 0.1 Design | FP16 | 63.9 GB | 34 s | Runs well |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | Ideogram 4 | FP16 | 57.3 GB | 52 s | Slow |
Best Video models for the NVIDIA GB10 (128 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.5 (22B, video + audio) | FP16 | 82.5 GB | 3.2 min | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.3 | FP16 | 75.4 GB | 13.9 min | Slow |
| 82Great quality (A) · 82 of 100: how capable the model is at FP16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2 (19B, video + audio) | FP16 | 75.4 GB | 13.9 min | Slow |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at FP8, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax H3 (33B, video + audio) | FP8 | 66.8 GB | 32.5 min | Slow |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Kandinsky 6.0 Pro (29B, video + audio) | FP16 | 85.4 GB | 1.7 h | Very slow |
Best Decision models for the NVIDIA GB10 (128 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 4B | Q8_0 | 14.4 GB | 120 ms | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3.5 | F16 | 11.3 GB | 25 ms | Runs great |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | zerank-2 | Q8_0 | 14.4 GB | 120 ms | Runs great |
| 84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Intern-Decision 4B | Q8_0 | 14.7 GB | 83 ms | Runs great |
| 84Great quality (A) · 84 of 100: how capable the model is at F16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3 | F16 | 11.3 GB | 25 ms | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Shieldstral 1.0 3B | Q8_0 | 14.1 GB | 115 ms | Runs great |
| 82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | d1 3B | F16 | 16.1 GB | 79 ms | Runs great |
| 82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | mxbai-rerank-large v2 | F16 | 13.0 GB | 59 ms | Runs great |
Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.