Qualcomm · Snapdragon X Plus (X1P-42-100) · Laptop
Best AI Models for Snapdragon X Plus (8-core) Copilot+ PC (16 GB)
Runs 9B models at 14 tok/s; 14B only just fits in 12 GB, and 27–31B doesn't fit.
| # | Model | Speed | llmrun Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 13.8 t/s | 13.8 tok/s | Q4_K_M · 6.6 GB | |
| 2 | Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 26.9 t/s | 26.9 tok/s | Q4_K_M · 3.4 GB | |
| 3 | Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 30.9 t/s | 30.9 tok/s | Q4_K_M · 5.0 GB | |
| 4 | Q4_K_M · 7.9 GB · 16.6 t/s | 16.6 tok/s | Q4_K_M · 7.9 GB | |
| 5 | Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 76.6 t/s | 76.6 tok/s | Q4_K_M · 5.5 GB |
| # | Model | Speed | Coding Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Q4_K_M · 7.9 GB · 16.6 t/s | 16.6 tok/s | Q4_K_M · 7.9 GB | |
| 2 | Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 26.9 t/s | 26.9 tok/s | overall | Q4_K_M · 3.4 GB |
| 3 | Qwen3 8BAlibaba Q4_K_M · 7.6 GB · 15.9 t/s | 15.9 tok/s | overall | Q4_K_M · 7.6 GB |
| 4 | Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 76.6 t/s | 76.6 tok/s | Q4_K_M · 5.5 GB | |
| 5 | Gemma 4 E4B ITGoogle Q4_K_M · 5.6 GB · 16.5 t/s | 16.5 tok/s | Q4_K_M · 5.6 GB |
| # | Model | Speed | Reasoning Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Qwen3 8BAlibabaHow to run → Q4_K_M · 7.6 GB · 15.9 t/s | 15.9 tok/s | Q4_K_M · 7.6 GB | |
| 2 | Q4_K_M · 7.9 GB · 16.6 t/s | 16.6 tok/s | Q4_K_M · 7.9 GB | |
| 3 | Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 30.9 t/s | 30.9 tok/s | Q4_K_M · 5.0 GB | |
| 4 | Qwen2.5 7B InstructAlibaba Q4_K_M · 5.8 GB · 17.6 t/s | 17.6 tok/s | Q4_K_M · 5.8 GB | |
| 5 | Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 76.6 t/s | 76.6 tok/s | Q4_K_M · 5.5 GB |
| # | Model | Speed | Long context Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 26.9 t/s | 26.9 tok/s | Q4_K_M · 3.4 GB | |
| 2 | Q4_K_M · 7.9 GB · 16.6 t/s | 16.6 tok/s | Q4_K_M · 7.9 GB | |
| 3 | Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 76.6 t/s | 76.6 tok/s | Q4_K_M · 5.5 GB | |
| 4 | Gemma 4 E4B ITGoogle Q4_K_M · 5.6 GB · 16.5 t/s | 16.5 tok/s | Q4_K_M · 5.6 GB | |
| 5 | Gemma 4 E2B ITGoogle Q4_K_M · 3.5 GB · 25.6 t/s | 25.6 tok/s | Q4_K_M · 3.5 GB |
| # | Model | Speed ↓ | llmrun Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 26.9 t/s | 26.9 tok/s | Q4_K_M · 3.4 GB | |
| 2 | Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 76.6 t/s | 76.6 tok/s | Q4_K_M · 5.5 GB | |
| 3 | Gemma 4 E2B ITGoogle Q4_K_M · 3.5 GB · 25.6 t/s | 25.6 tok/s | Q4_K_M · 3.5 GB | |
| 4 | Gemma 4 E4B ITGoogle Q4_K_M · 5.6 GB · 16.5 t/s | 16.5 tok/s | Q4_K_M · 5.6 GB | |
| 5 | Qwen3 8BAlibaba Q4_K_M · 7.6 GB · 15.9 t/s | 15.9 tok/s | Q4_K_M · 7.6 GB |
| # | Model | Speed | Vision Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 26.9 t/s | 26.9 tok/s | Q4_K_M · 3.4 GB | |
| 2 | Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 30.9 t/s | 30.9 tok/s | Q4_K_M · 5.0 GB | |
| 3 | Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 13.8 t/s | 13.8 tok/s | Q4_K_M · 6.6 GB | |
| 4 | MiniCPM V 4.7 1BOpenBMB Q4_K_M · 1.6 GB · 68.6 t/s | 68.6 tok/s | Q4_K_M · 1.6 GB | |
| 5 | LFM3 Omni 2BLiquid AI Q4_K_M · 2.4 GB · 51.6 t/s | 51.6 tok/s | Q4_K_M · 2.4 GB |
The Snapdragon X Plus (8-core) Copilot+ PC is a mid-range 16 GB laptop: it runs 9B models at 14 tok/s. The system keeps about 4 GB, leaving 12 GB for models. Prompt reading is its weak spot: a 4K-token prompt waits 78 s before the first word on Qwen3.5 9B. Snapdragon X Plus (X1P-42-100), released 2024.
Snapdragon X Plus (8-core) Copilot+ PC strengths and weaknesses
Weaknesses
- 27–31B models don't fit: Qwen3.8 27B needs 17.9 GB at Q4 vs 12 GB usable here
- Little room for context: Qwen3 14B uses 11.9 of 12 GB usable, 0.1 GB left
- Slow prompt reading: A 32K-token prompt on Qwen3.5 9B waits 10.3 min for the first token
Memory for models
12 GB of 16 GB27–31B models need 17.9 GB at Q4, more than the 12 GB available.Or rent an RTX 3090 (24 GB) from $0.18/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 Qwen3.5 9B.
Output speed depends on memory bandwidth (135 GB/s). Grey rows need more than the 12 GB available.
- 9BQwen3.5 9B · Q4_K_M · 6.6 GB13.8tok/s
- 9.2tok/s
- 27–31BQwen3.8 27B · not at 4-bitneeds 17.9 GB
- 35B MoEQwen3.6 35B A3B · not at 4-bitneeds 22.0 GB
- 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 278 models on the Snapdragon X Plus (8-core) Copilot+ PC
Featured onlyBest quant that fits in 12 GB, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works
| Model | Quant | VRAM | Speed | Context | Score | Fit |
|---|---|---|---|---|---|---|
Chatglm3 6BChat | Q4_K_M | 5.2 GB | 21.3 t/s | 8K | B62, Decent | |
Granite 4.0 MicroChatFunctions | Q4_K_M | 3.7 GB | 35.0 t/s | 131K | A73, Runs well | |
Qwen3 VL 4B ThinkingVisionFunctions | Q4_K_M | 4.5 GB | 27.9 t/s | 262K | A69, Runs well | |
Mistral 7B Instruct v0.3ChatFunctions | Q4_K_M | 6.8 GB | 17.8 t/s | 33K | B58, Decent | |
Nanonets OCR SVision | Q4_K_M | 3.2 GB | 33.4 t/s | 128K | A72, Runs well | |
GOT OCR2 0Vision | Q4_K_M | 2.3 GB | 94.4 t/s | 33K | S90, Runs great | |
Phi 4 ReasoningChatMathCodeReasoning | Q4_K_S | 11.9 GB | 9.8 t/s | 33K | D18, Barely runs | |
| Q4_K_M | 5.0 GB | 19.0 t/s | 4K | B59, Decent | ||
| Q4_K_M | 5.7 GB | 17.9 t/s | 8K | B58, Decent | ||
| Q4_K_M | 5.7 GB | 17.9 t/s | 8K | B58, Decent | ||
Llama 3.1 8BChat | Q4_K_M | 7.9 GB | 16.6 t/s | — | B56, Decent | |
Yi Coder 9B ChatChatCode | Q4_K_M | 7.2 GB | 15.1 t/s | 131K | B55, Decent | |
Qwen3 Coder 30B A3B InstructChatCodeFunctions | IQ2_M | 11.4 GB | 54.9 t/s | 262K | B59, Decent | |
Qwen2.5 Omni 7BChat | Q4_K_M | 9.9 GB | 12.4 t/s | — | B49, Decent | |
Qwen2.5 7B InstructChatFunctions | Q4_K_M | 5.8 GB | 17.6 t/s | 33K | B57, Decent |
Specs
- Chip
- Snapdragon X Plus (X1P-42-100) · Qualcomm Adreno X1-45
- CPU cores
- 8
- Unified memory
- 16 GB LPDDR5X-8448
- For models
- 12 GB (The system keeps 4 GB)
- Memory bandwidth
- 135 GB/s
- FP16 (dense)
- 3.4 TFLOPS
- NPU
- Hexagon NPU (45 TOPS)
- Released
- 2024-09-04
Snapdragon X Plus (8-core) Copilot+ PC FAQ
How much memory is available for AI on the Snapdragon X Plus (8-core) Copilot+ PC?
About 12 GB of the 16 GB. The system keeps roughly 4 GB for itself and other apps.
What is the largest model the Snapdragon X Plus (8-core) Copilot+ PC can run?
GPT OSS 20B (20.9B) is the largest at 4-bit or better: at IQ4_XS it uses 11.8 GB, 99% of the available memory, and runs at about 34.6 tok/s.
Can the Snapdragon X Plus (8-core) Copilot+ PC run Qwen3.5 9B?
Yes. Qwen3.5 9B fits at Q4_K_M, using 6.6 GB of the 12 GB available, and it is the best model that runs well on this machine.
Can the Snapdragon X Plus (8-core) Copilot+ PC run 27–31B models?
No. Qwen3.8 27B needs 17.9 GB at Q4, more than the 12 GB available.
How long does the Snapdragon X Plus (8-core) Copilot+ PC take to read a long prompt?
On Qwen3.5 9B, about 78 s for a 4K-token prompt and 10.3 min for a 32K-token document before the first word appears.
Is renting a GPU cheaper than buying the Snapdragon X Plus (8-core) Copilot+ PC?
An RTX 3090 (24 GB) rents from $0.14/hr.