NVIDIA · RTX Spark N1X · Laptop
Best AI Models for NVIDIA RTX Spark N1X Laptop (32 GB)
Runs 14B and 35B MoE models well; dense 27–31B fits but is slow at 11 tok/s, and 70B doesn't fit in 24 GB.
| # | Model | Speed | llmrun Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 11.2 t/s | 11.2 tok/s | Q4_K_M · 17.9 GB | |
| 2 | Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 11.2 t/s | 11.2 tok/s | Q4_K_M · 17.9 GB | |
| 3 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 63.7 t/s | 63.7 tok/s | Q4_K_M · 16.5 GB | |
| 4 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 68.6 t/s | 68.6 tok/s | Q4_K_M · 13.1 GB | |
| 5 | Q4_K_M · 19.3 GB · 97.5 t/s | 97.5 tok/s | Q4_K_M · 19.3 GB |
| # | Model | Speed | Coding Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Qwen3.6 35B A3BAlibabaHow to run → Q4_K_M · 22.0 GB · 58.8 t/s | 58.8 tok/s | Q4_K_M · 22.0 GB | |
| 2 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 63.7 t/s | 63.7 tok/s | Q4_K_M · 16.5 GB | |
| 3 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 68.6 t/s | 68.6 tok/s | Q4_K_M · 13.1 GB | |
| 4 | Q4_K_M · 7.9 GB · 36.9 t/s | 36.9 tok/s | Q4_K_M · 7.9 GB | |
| 5 | Q4_K_M · 19.3 GB · 97.5 t/s | 97.5 tok/s | Q4_K_M · 19.3 GB |
| # | Model | Speed | Reasoning Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Qwen3.6 35B A3BAlibabaHow to run → Q4_K_M · 22.0 GB · 58.8 t/s | 58.8 tok/s | Q4_K_M · 22.0 GB | |
| 2 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 63.7 t/s | 63.7 tok/s | Q4_K_M · 16.5 GB | |
| 3 | Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 30.7 t/s | 30.7 tok/s | Q4_K_M · 6.6 GB | |
| 4 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 68.6 t/s | 68.6 tok/s | Q4_K_M · 13.1 GB | |
| 5 | Q4_K_M · 19.3 GB · 97.5 t/s | 97.5 tok/s | Q4_K_M · 19.3 GB |
| # | Model | Speed | Math Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Qwen3.6 35B A3BAlibabaHow to run → Q4_K_M · 22.0 GB · 58.8 t/s | 58.8 tok/s | Q4_K_M · 22.0 GB | |
| 2 | Qwen3.8 27BAlibaba Q4_K_M · 17.9 GB · 11.2 t/s | 11.2 tok/s | Q4_K_M · 17.9 GB | |
| 3 | Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 11.2 t/s | 11.2 tok/s | Q4_K_M · 17.9 GB | |
| 4 | Q4_K_M · 19.3 GB · 97.5 t/s | 97.5 tok/s | Q4_K_M · 19.3 GB | |
| 5 | GLM 4.7 FlashZ.ai Q4_K_M · 19.9 GB · 57.0 t/s | 57.0 tok/s | Q4_K_M · 19.9 GB |
| # | Model | Speed | Long context Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Q4_K_M · 16.5 GB · 63.7 t/s | 63.7 tok/s | Q4_K_M · 16.5 GB | |
| 2 | Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 30.7 t/s | 30.7 tok/s | Q4_K_M · 6.6 GB | |
| 3 | Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 60.0 t/s | 60.0 tok/s | Q4_K_M · 3.4 GB | |
| 4 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 68.6 t/s | 68.6 tok/s | Q4_K_M · 13.1 GB | |
| 5 | LFM2.5 24B A2BLiquid AI Q4_K_M · 15.0 GB · 100 t/s | 100 tok/s | Q4_K_M · 15.0 GB |
| # | Model | Speed ↓ | llmrun Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Q4_K_M · 19.4 GB · 76.0 t/s | 76.0 tok/s | Q4_K_M · 19.4 GB | |
| 2 | Q4_K_M · 19.3 GB · 97.5 t/s | 97.5 tok/s | Q4_K_M · 19.3 GB | |
| 3 | Qwen3 30B A3B Instruct 2507Alibaba Q4_K_M · 19.4 GB · 76.0 t/s | 76.0 tok/s | Q4_K_M · 19.4 GB | |
| 4 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 68.6 t/s | 68.6 tok/s | Q4_K_M · 13.1 GB | |
| 5 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 63.7 t/s | 63.7 tok/s | Q4_K_M · 16.5 GB |
The NVIDIA RTX Spark N1X Laptop is one of the fastest 32 GB machines: it runs 14B and 35B MoE models well. Among 32 GB machines, only the M1 Max and M2 Max write faster. Windows 11 on Arm keeps about 8 GB, leaving 24 GB for models. With 125 TFLOPS it reads long prompts faster than most 32 GB machines: a 4K-token prompt takes 4.0 s. RTX Spark N1X (Blackwell), released 2026.
NVIDIA RTX Spark N1X Laptop strengths and weaknesses
Strengths
- Runs 35B MoE models: Qwen3.6 35B A3B at 58.8 tok/s in 22 GB
- Low power draw: 80 W at full load for the whole machine
Weaknesses
- 70B models don't fit: Llama 3.3 70B Instruct needs 51.3 GB at Q4 vs 24 GB usable here
- Slow on large dense models: Qwen3.8 27B at 11.2 tok/s
Memory for models
24 GB of 32 GB70B models need 51.3 GB at Q4, more than the 24 GB available.Or rent an A100 (80 GB) from $1.10/hr →
The same chip from other makers first, then machines and GPUs people weigh against it, each with the one reason it is worth a look. Speeds on Qwen3.6 35B A3B.
Output speed depends on memory bandwidth (301 GB/s). Grey rows need more than the 24 GB available.
- 9BQwen3.5 9B · Q4_K_M · 6.6 GB30.7tok/s
- 14BQwen3 14B · Q4_K_M · 11.9 GB20.6tok/s
- 27–31BQwen3.8 27B · Q4_K_M · 17.9 GB11.2tok/s
- 35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB58.8tok/s
- 70BLlama 3.3 70B Instruct · not at 4-bitneeds 51.3 GB
- 120B MoEGPT OSS 120B · not at 4-bitneeds 70.8 GB
Estimated speeds: Q4_K_M, 4K context, one user. How we estimate
All 1158 models on the NVIDIA RTX Spark N1X Laptop
Featured onlyBest quant that fits in 24 GB, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works
| Model | Quant | VRAM | Speed | Context | Score | Fit |
|---|---|---|---|---|---|---|
ALoDLM 8BChatCodeFunctions | Q4_K_M | 7.6 GB | 35.4 t/s | 41K | A73, Runs well | |
Edge0 35B A3B PreviewChatFunctions | Q4_K_M | 21.3 GB | 76.9 t/s | 262K | A75, Runs well | |
Ornith 1.5 9BChatFunctions | Q4_K_M | 6.6 GB | 30.7 t/s | 262K | A71, Runs well | |
Tiny Qwen3ForCausalLM Instruct 2507ChatFunctions | Q4_K_M | 0.5 GB | 651.7 t/s | 262K | S100, Runs great | |
LensVLM 9BVisionFunctions | Q4_K_M | 6.5 GB | 31.5 t/s | 262K | A71, Runs well | |
Underdog Saluki 27B 1.0ChatFunctions | Q4_K_M | 21.4 GB | 11.0 t/s | — | C37, Usable | |
| BF16 | 0.4 GB | 454.7 t/s | 1K | S100, Runs great | ||
Qwen3.8 4B DistillChatReasoningFunctions | Q4_K_M | 3.4 GB | 60.0 t/s | 262K | A84, Runs well | |
Nanbeige4.2 3BChatFunctions | Q4_K_M | 3.5 GB | 67.7 t/s | 262K | S85, Runs great | |
Distil Lfm25 ShellperChatFunctions | Q4_K_M | 0.8 GB | 337.1 t/s | 128K | S100, Runs great | |
Qwen3 30B A3B Thinking 2507ChatFunctions | Q4_K_M | 19.4 GB | 76.0 t/s | 262K | S86, Runs great | |
OCC RAG 1.7BChat | Q4_K_M | 3.2 GB | 124.5 t/s | 33K | S95, Runs great | |
| Q4_K_M | 16.5 GB | 63.7 t/s | 262K | A84, Runs well | ||
| Q4_K_M | 0.9 GB | 283.4 t/s | 8K | S100, Runs great | ||
Wald 4BChatReasoningFunctions | Q4_K_M | 3.4 GB | 60.0 t/s | 262K | A84, Runs well |
Specs
- Chip
- RTX Spark N1X · NVIDIA RTX Spark N1X
- CPU cores
- 20
- GPU cores
- 6,144
- Unified memory
- 32 GB LPDDR5X-9400 (soldered, unified)
- For models
- 24 GB (Windows 11 on Arm keeps 8 GB)
- Memory bandwidth
- 300.8 GB/s
- FP16 (dense)
- 125 TFLOPS
- NPU
- NVIDIA NPU (TOPS not published)
- Power
- 80 W max
- OS
- Windows 11 on Arm
- Released
- 2026-10-16
NVIDIA RTX Spark N1X Laptop FAQ
How much memory is available for AI on the NVIDIA RTX Spark N1X Laptop (32 GB)?
About 24 GB of the 32 GB. Windows 11 on Arm keeps roughly 8 GB for itself and other apps.
What is the largest model the NVIDIA RTX Spark N1X Laptop (32 GB) can run?
Qwen3.6 35B A3B (36.0B) is the largest at 4-bit or better: at Q4_K_M it uses 22.0 GB, 92% of the available memory, and runs at about 58.8 tok/s.
Can the NVIDIA RTX Spark N1X Laptop (32 GB) run Qwen3.8 27B?
Yes. Qwen3.8 27B fits at Q4_K_M, using 17.9 GB of the 24 GB available, and it is the best model that runs well on this machine.
Can the NVIDIA RTX Spark N1X Laptop (32 GB) run 70B models?
No. Llama 3.3 70B Instruct needs 51.3 GB at Q4, more than the 24 GB available.
How long does the NVIDIA RTX Spark N1X Laptop (32 GB) take to read a long prompt?
On Qwen3.8 27B, about 4.0 s for a 4K-token prompt and 32 s for a 32K-token document before the first word appears.
Is renting a GPU cheaper than buying the NVIDIA RTX Spark N1X Laptop?
An RTX 5090 (32 GB) rents from $0.47/hr.