Intel · Core Ultra 5 226V · Laptop
Best AI Models for Intel Core Ultra 5 226V (Lunar Lake, 16 GB) Laptop
Runs 9B models at 11 tok/s; 14B only just fits in 11 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 · 10.7 t/s | 10.7 tok/s | Q4_K_M · 6.6 GB | |
| 2 | Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 20.9 t/s | 20.9 tok/s | Q4_K_M · 3.4 GB | |
| 3 | Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 24.0 t/s | 24.0 tok/s | Q4_K_M · 5.0 GB | |
| 4 | Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 54.1 t/s | 54.1 tok/s | Q4_K_M · 5.5 GB | |
| 5 | Gemma 4 E2B ITGoogle Q4_K_M · 3.5 GB · 19.9 t/s | 19.9 tok/s | Q4_K_M · 3.5 GB |
| # | Model | Speed | Reasoning Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Q4_K_M · 5.0 GB · 24.0 t/s | 24.0 tok/s | Q4_K_M · 5.0 GB | |
| 2 | Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 10.7 t/s | 10.7 tok/s | Q4_K_M · 6.6 GB | |
| 3 | Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 20.9 t/s | 20.9 tok/s | overall | Q4_K_M · 3.4 GB |
| 4 | Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 54.1 t/s | 54.1 tok/s | Q4_K_M · 5.5 GB | |
| 5 | Gemma 4 E2B ITGoogle Q4_K_M · 3.5 GB · 19.9 t/s | 19.9 tok/s | Q4_K_M · 3.5 GB |
| # | Model | Speed | Long context Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 20.9 t/s | 20.9 tok/s | Q4_K_M · 3.4 GB | |
| 2 | Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 54.1 t/s | 54.1 tok/s | Q4_K_M · 5.5 GB | |
| 3 | Qwen3.5 2BAlibaba Q4_K_M · 1.9 GB · 38.6 t/s | 38.6 tok/s | Q4_K_M · 1.9 GB | |
| 4 | Gemma 4 E2B ITGoogle Q4_K_M · 3.5 GB · 19.9 t/s | 19.9 tok/s | Q4_K_M · 3.5 GB | |
| 5 | MiniCPM5 2BOpenBMB Q4_K_M · 2.5 GB · 35.9 t/s | 35.9 tok/s | Q4_K_M · 2.5 GB |
| # | Model | Speed | Vision Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 20.9 t/s | 20.9 tok/s | Q4_K_M · 3.4 GB | |
| 2 | Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 24.0 t/s | 24.0 tok/s | Q4_K_M · 5.0 GB | |
| 3 | Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 10.7 t/s | 10.7 tok/s | Q4_K_M · 6.6 GB | |
| 4 | MiniCPM V 4.7 1BOpenBMB Q4_K_M · 1.6 GB · 53.3 t/s | 53.3 tok/s | Q4_K_M · 1.6 GB | |
| 5 | LFM3 Omni 2BLiquid AI Q4_K_M · 2.4 GB · 40.1 t/s | 40.1 tok/s | Q4_K_M · 2.4 GB |
The Intel Core Ultra 5 226V (Lunar Lake, 16 GB) Laptop is a mid-range 16 GB laptop: it runs 9B models at 11 tok/s. The system keeps about 5 GB, leaving 11 GB for models. With 27 TFLOPS it reads long prompts faster than most 16 GB machines: a 4K-token prompt takes 17 s. Core Ultra 5 226V, released 2024.
Intel Core Ultra 5 226V (Lunar Lake, 16 GB) Laptop strengths and weaknesses
Strengths
- Low power draw: 17 W at full load for the whole machine
Weaknesses
- 27–31B models don't fit: Qwen3.8 27B needs 17.9 GB at Q4 vs 11 GB usable here
- Little room for context: Qwen3 14B uses 10.9 of 11 GB usable, 0.1 GB left
- Slow prompt reading: A 32K-token prompt on Qwen3.5 9B waits 2.2 min for the first token
- oneAPI, not CUDA: No FP8 or NVFP4 weights and no vLLM AWQ or GPTQ; use GGUF builds
Memory for models
11 GB of 16 GB27–31B models need 17.9 GB at Q4, more than the 11 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 (137 GB/s). Grey rows need more than the 11 GB available.
- 9BQwen3.5 9B · Q4_K_M · 6.6 GB10.7tok/s
- 8.0tok/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 956 models on the Intel Core Ultra 5 226V (Lunar Lake, 16 GB) Laptop
Featured onlyBest quant that fits in 11 GB, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works
| Model | Quant | VRAM | Speed | Context | Score | Fit |
|---|---|---|---|---|---|---|
Qwen2.5 14B InstructChatFunctions | Q4_0 | 10.9 GB | 8.4 t/s | 33K | D16, Barely runs | |
| Q4_K_M | 7.7 GB | 10.6 t/s | 8K | B49, Decent | ||
Nemotron Mini 4B InstructChatFunctions | Q4_K_M | 3.2 GB | 23.0 t/s | 4K | B63, Decent | |
DeepSeek v2 LiteChat | Q4_K_M | 10.2 GB | 32.6 t/s | 164K | B53, Decent | |
Yi 6BChat | Q4_K_M | 4.2 GB | 16.8 t/s | 4K | B56, Decent | |
Falcon Mamba 7BChat | Q4_K_M | 7.3 GB | 14.2 t/s | — | B53, Decent | |
Devstral Small 2 24B Instruct 2512ChatFunctions | IQ2_XS | 10.9 GB | 8.6 t/s | 393K | D16, Barely runs | |
Mellum 4B BaseChatCode | Q4_K_M | 5.7 GB | 19.7 t/s | 8K | B60, Decent | |
Qwen 1 8BChat | Q4_K_M | 1.9 GB | 56.4 t/s | 8K | A82, Runs well | |
Llama 2 7B HFChat | Q4_K_M | 6.9 GB | 15.3 t/s | — | B55, Decent | |
Qwen2.5 Coder 7BChatCodeFunctions | Q4_K_M | 5.8 GB | 13.7 t/s | 33K | B53, Decent | |
Phi 3 Mini 128k InstructChatCode | Q4_K_M | 9.0 GB | 20.1 t/s | 131K | B58, Decent | |
| Q4_K_M | 4.6 GB | 37.9 t/s | 33K | A74, Runs well | ||
Shieldgemma 2BChat | Q4_K_M | 3.6 GB | 39.5 t/s | — | A75, Runs well | |
Qwen2 0.5BChat | Q4_K_M | 0.8 GB | 110.1 t/s | 131K | S93, Runs great |
Specs
- Chip
- Core Ultra 5 226V · Intel Arc 130V
- CPU cores
- 8
- GPU cores
- 7
- Unified memory
- 16 GB LPDDR5X-8533 (on-package)
- For models
- 11 GB (The system keeps 5 GB)
- Memory bandwidth
- 136.5 GB/s
- FP16 (dense)
- 26.5 TFLOPS
- NPU
- Intel AI Boost NPU 4 (40 TOPS)
- Power
- 17 W max
- Released
- 2024-09-24
Intel Core Ultra 5 226V (Lunar Lake, 16 GB) Laptop FAQ
How much memory is available for AI on the Intel Core Ultra 5 226V (Lunar Lake, 16 GB) Laptop?
About 11 GB of the 16 GB. The system keeps roughly 5 GB for itself and other apps.
What is the largest model the Intel Core Ultra 5 226V (Lunar Lake, 16 GB) Laptop can run?
Phi 4 (14.7B) is the largest at 4-bit or better: at Q4_0 it uses 11.0 GB, 100% of the available memory, and runs at about 8.5 tok/s.
Can the Intel Core Ultra 5 226V (Lunar Lake, 16 GB) Laptop run Qwen3.5 9B?
Yes. Qwen3.5 9B fits at Q4_K_M, using 6.6 GB of the 11 GB available, and it is the best model that runs well on this machine.
Can the Intel Core Ultra 5 226V (Lunar Lake, 16 GB) Laptop run 27–31B models?
No. Qwen3.8 27B needs 17.9 GB at Q4, more than the 11 GB available.
How long does the Intel Core Ultra 5 226V (Lunar Lake, 16 GB) Laptop take to read a long prompt?
On Qwen3.5 9B, about 17 s for a 4K-token prompt and 2.2 min for a 32K-token document before the first word appears.
Is renting a GPU cheaper than buying the Intel Core Ultra 5 226V (Lunar Lake, 16 GB) Laptop?
An RTX 3090 (24 GB) rents from $0.17/hr.