Intel · Core Ultra 9 288V · Laptop
Best AI Models for Intel Core Ultra 9 288V (Lunar Lake) Laptop (32 GB)
Runs 35B MoE models well; 9B, 14B and 27–31B fit but are slow (11, 7 and 4 tok/s), and 70B doesn't fit in 24 GB.
| # | Model | Speed | llmrun Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Qwen3.6 35B A3BAlibabaHow to run → Q4_K_M · 22.0 GB · 19.8 t/s | 19.8 tok/s | Q4_K_M · 22.0 GB | |
| 2 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 21.6 t/s | 21.6 tok/s | Q4_K_M · 16.5 GB | |
| 3 | Qwen3 30B A3B Thinking 2507Alibaba Q4_K_M · 19.4 GB · 25.2 t/s | 25.2 tok/s | Q4_K_M · 19.4 GB | |
| 4 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 23.4 t/s | 23.4 tok/s | Q4_K_M · 13.1 GB | |
| 5 | Q4_K_M · 19.3 GB · 31.7 t/s | 31.7 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 · 19.8 t/s | 19.8 tok/s | Q4_K_M · 22.0 GB | |
| 2 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 21.6 t/s | 21.6 tok/s | Q4_K_M · 16.5 GB | |
| 3 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 23.4 t/s | 23.4 tok/s | Q4_K_M · 13.1 GB | |
| 4 | Qwen3 30B A3B Thinking 2507Alibaba Q4_K_M · 19.4 GB · 25.2 t/s | 25.2 tok/s | overall | Q4_K_M · 19.4 GB |
| 5 | Q4_K_M · 19.3 GB · 31.7 t/s | 31.7 tok/s | Q4_K_M · 19.3 GB |
| # | Model | Speed | Long context Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Q4_K_M · 16.5 GB · 21.6 t/s | 21.6 tok/s | Q4_K_M · 16.5 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 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 23.4 t/s | 23.4 tok/s | Q4_K_M · 13.1 GB | |
| 4 | Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 19.8 t/s | 19.8 tok/s | Q4_K_M · 22.0 GB | |
| 5 | LFM2.5 24B A2BLiquid AI Q4_K_M · 15.0 GB · 33.0 t/s | 33.0 tok/s | Q4_K_M · 15.0 GB |
| # | Model | Speed ↓ | llmrun Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Q4_K_M · 19.4 GB · 25.2 t/s | 25.2 tok/s | Q4_K_M · 19.4 GB | |
| 2 | Q4_K_M · 19.3 GB · 31.7 t/s | 31.7 tok/s | Q4_K_M · 19.3 GB | |
| 3 | Qwen3 30B A3B Instruct 2507Alibaba Q4_K_M · 19.4 GB · 25.2 t/s | 25.2 tok/s | Q4_K_M · 19.4 GB | |
| 4 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 23.4 t/s | 23.4 tok/s | Q4_K_M · 13.1 GB | |
| 5 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 21.6 t/s | 21.6 tok/s | Q4_K_M · 16.5 GB |
| # | Model | Speed | Vision Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Qwen3.6 35B A3BAlibabaHow to run → Q4_K_M · 22.0 GB · 19.8 t/s | 19.8 tok/s | Q4_K_M · 22.0 GB | |
| 2 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 21.6 t/s | 21.6 tok/s | Q4_K_M · 16.5 GB | |
| 3 | Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 20.9 t/s | 20.9 tok/s | Q4_K_M · 3.4 GB | |
| 4 | Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 24.0 t/s | 24.0 tok/s | Q4_K_M · 5.0 GB | |
| 5 | MiniCPM V 4.7 35B A3BOpenBMB Q4_K_M · 22.1 GB · 22.8 t/s | 22.8 tok/s | Q4_K_M · 22.1 GB |
The Intel Core Ultra 9 288V (Lunar Lake) Laptop is a 32 GB laptop with more memory than speed: it runs 35B MoE models well. The system keeps about 8 GB, leaving 24 GB for models. With 34 TFLOPS it reads long prompts faster than most 32 GB machines: a 4K-token prompt takes 6.4 s. Core Ultra 9 288V, released 2024.
Intel Core Ultra 9 288V (Lunar Lake) Laptop strengths and weaknesses
Strengths
- Runs 35B MoE models: Qwen3.6 35B A3B at 19.8 tok/s in 22 GB
- Low power draw: 30 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 3.9 tok/s
- Slow prompt reading: A 32K-token prompt on Qwen3.6 35B A3B waits 51.0 s for the first token
- oneAPI, not CUDA: No FP8 or NVFP4 weights and no vLLM AWQ or GPTQ; use GGUF builds
Memory for models
24 GB of 32 GB70B models need 51.3 GB at Q4, more than the 24 GB available.Or rent an H100 (80 GB) from $2.20/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 (137 GB/s). Grey rows need more than the 24 GB available.
- 9BQwen3.5 9B · Q4_K_M · 6.6 GB10.7tok/s
- 7.2tok/s
- 3.9tok/s
- 35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB19.8tok/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 1141 models on the Intel Core Ultra 9 288V (Lunar Lake) 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 |
|---|---|---|---|---|---|---|
LFM2 8B A1BChat | Q4_K_M | 5.5 GB | 51.1 t/s | 128K | A80, Runs well | |
Yi Coder 9B ChatChatCode | Q4_K_M | 7.2 GB | 11.8 t/s | 131K | B51, Decent | |
Qwen3 Code Reasoning 4BChatCodeReasoning | Q4_K_M | 4.2 GB | 23.6 t/s | 262K | B64, Decent | |
| Q4_K_M | 3 GB | 30.3 t/s | 4K | A71, Runs well | ||
| Q4_K_M | 7.3 GB | 12.7 t/s | 131K | B51, Decent | ||
Qwen2.5 Math 1.5B InstructChatMathFunctions | Q4_K_M | 1.3 GB | 53.3 t/s | 4K | A81, Runs well | |
Qwen2.5 7B InstructChatFunctions | Q4_K_M | 5.8 GB | 13.7 t/s | 33K | B53, Decent | |
Kolibri 1 BF16ChatReasoningFunctions | IQ2_XXS | 22.5 GB | 41.3 t/s | 262K | B55, Decent | |
| Q4_K_M | 11.8 GB | 7.7 t/s | 262K | B45, Decent | ||
Aya Expanse 8BChat | BF16 | 20.2 GB | 3.9 t/s | — | C35, Usable | |
OLMo 2 0425 1BChat | Q4_K_M | 1.7 GB | 46.7 t/s | 4K | A78, Runs well | |
Gemma 3 270M ITChat | Q4_K_M | 1.2 GB | 379.2 t/s | — | S100, Runs great | |
Instella 3BChat | BF16 | 8.0 GB | 9.4 t/s | 4K | B47, Decent | |
| Q4_K_M | 6.0 GB | 11.3 t/s | 131K | B50, Decent | ||
Yi 1.5 6B ChatChat | Q4_K_M | 4.2 GB | 16.8 t/s | 4K | B56, Decent |
Specs
- Chip
- Core Ultra 9 288V · Intel Arc 140V
- CPU cores
- 8
- GPU cores
- 8
- Unified memory
- 32 GB LPDDR5X-8533 (on-package)
- For models
- 24 GB (The system keeps 8 GB)
- Memory bandwidth
- 136.5 GB/s
- FP16 (dense)
- 33.6 TFLOPS
- NPU
- Intel AI Boost NPU 4 (48 TOPS)
- Power
- 30 W max
- Released
- 2024-09-24
Intel Core Ultra 9 288V (Lunar Lake) Laptop FAQ
How much memory is available for AI on the Intel Core Ultra 9 288V (Lunar Lake) Laptop?
About 24 GB of the 32 GB. The system keeps roughly 8 GB for itself and other apps.
What is the largest model the Intel Core Ultra 9 288V (Lunar Lake) Laptop 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 19.8 tok/s.
Can the Intel Core Ultra 9 288V (Lunar Lake) Laptop 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 Intel Core Ultra 9 288V (Lunar Lake) Laptop take to read a long prompt?
On Qwen3.6 35B A3B, about 6.4 s for a 4K-token prompt and 51 s for a 32K-token document before the first word appears.
Is renting a GPU cheaper than buying the Intel Core Ultra 9 288V (Lunar Lake) Laptop?
An RTX 5090 (32 GB) rents from $0.50/hr.