NVIDIA · RTX Spark N1X · Laptop
Best AI Models for NVIDIA RTX Spark N1X Laptop (128 GB)
Runs 14B and 120B MoE models well; 27–31B and 70B fit but are slow (11 and 4 tok/s).
| # | Model | Speed | llmrun 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 30B A3B Thinking 2507Alibaba Q4_K_M · 19.4 GB · 76.0 t/s | 76.0 tok/s | Q4_K_M · 19.4 GB | |
| 4 | GLM 4.5 AirZ.ai Q4_K_M · 67.6 GB · 20.5 t/s | 20.5 tok/s | Q4_K_M · 67.6 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 | GPT OSS 120BOpenAI Q4_K_M · 70.8 GB · 50.7 t/s | 50.7 tok/s | Q4_K_M · 70.8 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 120BOpenAI Q4_K_M · 70.8 GB · 50.7 t/s | 50.7 tok/s | Q4_K_M · 70.8 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 ↓ | 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 |
| # | Model | Speed | Agents Score | Quant · Memory |
|---|---|---|---|---|
| 1 | GPT OSS 120BOpenAIHow to run → Q4_K_M · 70.8 GB · 50.7 t/s | 50.7 tok/s | Q4_K_M · 70.8 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 35B A3BAlibaba Q4_K_M · 22.0 GB · 58.8 t/s | 58.8 tok/s | overall | Q4_K_M · 22.0 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 |
The NVIDIA RTX Spark N1X Laptop is a 128 GB laptop with more memory than speed: it runs 14B and 120B MoE models well. Windows 11 on Arm keeps about 32 GB, leaving 96 GB for models. With 125 TFLOPS it reads long prompts faster than most 128 GB machines: a 4K-token prompt takes 690 ms. RTX Spark N1X (Blackwell), released 2026.
NVIDIA RTX Spark N1X Laptop strengths and weaknesses
Strengths
- Runs 120B MoE models: GPT OSS 120B at 50.7 tok/s in 70.8 GB
- Reads long prompts fast: A 32K-token prompt on Qwen3.6 35B A3B starts answering in 5.5 s
- Low power draw: 80 W at full load for the whole machine
Weaknesses
- Slow on large dense models: Llama 3.3 70B Instruct at 4.2 tok/s, Qwen3.8 27B at 11.2 tok/s
Memory for models
96 GB of 128 GBEverything on the size ladder fits. Qwen3.6 35B A3B and Gemma 4 26B A4B IT together use 38.5 GB and leave 57.5 GB free.
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 96 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
- 4.2tok/s
- 120B MoEGPT OSS 120B · Q4_K_M · 70.8 GB50.7tok/s
Estimated speeds: Q4_K_M, 4K context, one user. How we estimate
All 1283 models on the NVIDIA RTX Spark N1X Laptop
Featured onlyBest quant that fits in 96 GB, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works
| Model | Quant | VRAM | Speed | Context | Score | Fit |
|---|---|---|---|---|---|---|
LFM2.5 VL 450MVisionFunctions | Q4_K_M | 0.8 GB | 305.5 t/s | 128K | S100, Runs great | |
AREX 2VisionFunctionsReasoning | Q4_K_M | 17.6 GB | 11.4 t/s | 262K | B50, Decent | |
Supra 50M ReasoningChatReasoning | Q4_K_M | 0.3 GB | 543.1 t/s | 1K | S100, Runs great | |
LLaDA2.1 MiniChatFunctions | BF16 | 33.5 GB | 62.8 t/s | 33K | A84, Runs well | |
TwIL 8BChatReasoningMathCodeFunctions | Q4_K_M | 8.3 GB | 33.1 t/s | 131K | A72, Runs well | |
OneRec 1.7BChatFunctions | Q4_K_M | 3.5 GB | 108.0 t/s | 41K | S93, Runs great | |
Holo4 27BVisionFunctions | Q4_K_M | 17.6 GB | 11.4 t/s | 262K | B50, Decent | |
| BF16 | 0.9 GB | 325.9 t/s | 33K | S100, Runs great | ||
Tiny Qwen3MoeForCausalLMChatFunctions | Q4_K_M | 0.6 GB | 651.7 t/s | 41K | S100, Runs great | |
Qwen3 VL 235B A22B InstructVisionFunctions | IQ3_XXS | 93.2 GB | 19.8 t/s | 262K | C33, Usable | |
Qwopus3.5 9B v3VisionReasoningFunctions | Q4_K_M | 6.6 GB | 30.7 t/s | 262K | A71, Runs well | |
Tiny Random Gpt2Chat | Q4_K_M | 0.0 GB | 19552.0 t/s | 1K | S100, Runs great | |
| Q4_K_M | 4 GB | 55.1 t/s | 262K | A82, Runs well | ||
Opt 125MChat | FP16 | 0.3 GB | 698.3 t/s | 2K | S100, Runs great | |
Qwen3 VL 8B InstructVisionFunctions | Q4_K_M | 8.0 GB | 33.4 t/s | 262K | A72, Runs well |
Specs
- Chip
- RTX Spark N1X · NVIDIA RTX Spark N1X
- CPU cores
- 20
- GPU cores
- 6,144
- Unified memory
- 128 GB LPDDR5X-9400 (soldered, unified)
- For models
- 96 GB (Windows 11 on Arm keeps 32 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 (128 GB)?
About 96 GB of the 128 GB. Windows 11 on Arm keeps roughly 32 GB for itself and other apps.
What is the largest model the NVIDIA RTX Spark N1X Laptop (128 GB) can run?
Mistral Medium 3.5 128B (127.7B) is the largest at 4-bit or better: at Q4_K_M it uses 82.8 GB, 86% of the available memory, and runs at about 2.5 tok/s.
Can the NVIDIA RTX Spark N1X Laptop (128 GB) run Qwen3.6 35B A3B?
Yes. Qwen3.6 35B A3B fits at Q4_K_M, using 22.0 GB of the 96 GB available, and it is the best model that runs well on this machine.
Can the NVIDIA RTX Spark N1X Laptop (128 GB) run 70B models?
Yes, but slowly: Llama 3.3 70B Instruct at Q4_K_M uses 51.3 GB and writes about 4.2 tok/s.
How long does the NVIDIA RTX Spark N1X Laptop (128 GB) take to read a long prompt?
On Qwen3.6 35B A3B, about 690 ms for a 4K-token prompt and 5.5 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 PRO 6000 Blackwell Max-Q Workstation Edition (96 GB) rents from $1.00/hr.