Intel · Core Ultra X9 388H · Laptop
Best AI Models for Intel Core Ultra X9 388H (Panther Lake) Laptop (32 GB)
Runs 35B MoE models well; 9B, 14B and 27–31B fit but are slow (12, 8 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 · 21.9 t/s | 21.9 tok/s | Q4_K_M · 22.0 GB | |
| 2 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 23.9 t/s | 23.9 tok/s | Q4_K_M · 16.5 GB | |
| 3 | Qwen3 30B A3B Thinking 2507Alibaba Q4_K_M · 19.4 GB · 27.5 t/s | 27.5 tok/s | Q4_K_M · 19.4 GB | |
| 4 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 26.0 t/s | 26.0 tok/s | Q4_K_M · 13.1 GB | |
| 5 | Q4_K_M · 19.3 GB · 34.2 t/s | 34.2 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 · 21.9 t/s | 21.9 tok/s | Q4_K_M · 22.0 GB | |
| 2 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 23.9 t/s | 23.9 tok/s | Q4_K_M · 16.5 GB | |
| 3 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 26.0 t/s | 26.0 tok/s | Q4_K_M · 13.1 GB | |
| 4 | Qwen3 30B A3B Thinking 2507Alibaba Q4_K_M · 19.4 GB · 27.5 t/s | 27.5 tok/s | overall | Q4_K_M · 19.4 GB |
| 5 | Q4_K_M · 19.3 GB · 34.2 t/s | 34.2 tok/s | Q4_K_M · 19.3 GB |
| # | Model | Speed | Long context Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Q4_K_M · 16.5 GB · 23.9 t/s | 23.9 tok/s | Q4_K_M · 16.5 GB | |
| 2 | Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 23.6 t/s | 23.6 tok/s | Q4_K_M · 3.4 GB | |
| 3 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 26.0 t/s | 26.0 tok/s | Q4_K_M · 13.1 GB | |
| 4 | Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 21.9 t/s | 21.9 tok/s | Q4_K_M · 22.0 GB | |
| 5 | LFM2.5 24B A2BLiquid AI Q4_K_M · 15.0 GB · 36.0 t/s | 36.0 tok/s | Q4_K_M · 15.0 GB |
| # | Model | Speed ↓ | llmrun Score | Quant · Memory |
|---|---|---|---|---|
| 1 | Q4_K_M · 19.4 GB · 27.5 t/s | 27.5 tok/s | Q4_K_M · 19.4 GB | |
| 2 | Q4_K_M · 19.3 GB · 34.2 t/s | 34.2 tok/s | Q4_K_M · 19.3 GB | |
| 3 | Qwen3 30B A3B Instruct 2507Alibaba Q4_K_M · 19.4 GB · 27.5 t/s | 27.5 tok/s | Q4_K_M · 19.4 GB | |
| 4 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 26.0 t/s | 26.0 tok/s | Q4_K_M · 13.1 GB | |
| 5 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 23.9 t/s | 23.9 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 · 21.9 t/s | 21.9 tok/s | Q4_K_M · 22.0 GB | |
| 2 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 23.9 t/s | 23.9 tok/s | Q4_K_M · 16.5 GB | |
| 3 | Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 23.6 t/s | 23.6 tok/s | Q4_K_M · 3.4 GB | |
| 4 | Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 27.0 t/s | 27.0 tok/s | Q4_K_M · 5.0 GB | |
| 5 | MiniCPM V 4.7 35B A3BOpenBMB Q4_K_M · 22.1 GB · 25.1 t/s | 25.1 tok/s | Q4_K_M · 22.1 GB |
The Intel Core Ultra X9 388H (Panther Lake) Laptop is a mid-range 32 GB laptop: it runs 35B MoE models well. The system keeps about 8 GB, leaving 24 GB for models. With 61 TFLOPS it reads long prompts faster than most 32 GB machines: a 4K-token prompt takes 3.5 s. Core Ultra X9 388H, released 2026.
Intel Core Ultra X9 388H (Panther Lake) Laptop strengths and weaknesses
Strengths
- Runs 35B MoE models: Qwen3.6 35B A3B at 21.9 tok/s in 22 GB
- Low power draw: 25 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 4.4 tok/s
- 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 A100 (80 GB) from $1.07/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 (154 GB/s). Grey rows need more than the 24 GB available.
- 9BQwen3.5 9B · Q4_K_M · 6.6 GB12.1tok/s
- 8.1tok/s
- 4.4tok/s
- 35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB21.9tok/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 Intel Core Ultra X9 388H (Panther 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 |
|---|---|---|---|---|---|---|
Qwen2.5 7B InstructChatFunctions | Q4_K_M | 5.8 GB | 15.4 t/s | 33K | B55, Decent | |
Yi Coder 9B ChatChatCode | Q4_K_M | 7.2 GB | 13.2 t/s | 131K | B52, Decent | |
OLMo 2 0425 1BChat | Q4_K_M | 1.7 GB | 52.6 t/s | 4K | A81, Runs well | |
Kolibri 1 BF16ChatReasoningFunctions | IQ2_XXS | 22.5 GB | 44.2 t/s | 262K | B56, Decent | |
Qwen2.5 Coder 14B InstructChatCodeFunctions | Q4_K_M | 12.4 GB | 8.0 t/s | 33K | B45, Decent | |
Yi 1.5 6B ChatChat | Q4_K_M | 4.2 GB | 18.9 t/s | 4K | B59, Decent | |
Nemotron Labs Diffusion 8BChatFunctions | BF16 | 19.6 GB | 4.4 t/s | 262K | C38, Usable | |
| Q4_K_M | 4.5 GB | 24.5 t/s | 33K | A65, Runs well | ||
| Q4_K_M | 11.8 GB | 8.7 t/s | 262K | B46, Decent | ||
Kimi Linear 48B A3B InstructChatFunctions | IQ3_XXS | 23.4 GB | 42.2 t/s | — | C44, Usable | |
Aya Expanse 8BChat | BF16 | 20.2 GB | 4.3 t/s | — | C36, Usable | |
Instella 3BChat | BF16 | 8.0 GB | 10.5 t/s | 4K | B49, Decent | |
| Q4_K_M | 1.0 GB | 76.0 t/s | 2K | S87, Runs great | ||
Phi 4 Mini InstructChatCodeFunctions | Q4_K_M | 4.8 GB | 26.8 t/s | 131K | A68, Runs well | |
Polyglot Ko 1.3BChat | Q4_K_M | 0.9 GB | 80.8 t/s | 2K | S88, Runs great |
Specs
- Chip
- Core Ultra X9 388H · Intel Arc B390
- CPU cores
- 16
- GPU cores
- 12
- Unified memory
- 32 GB LPDDR5X-9600 (128-bit)
- For models
- 24 GB (The system keeps 8 GB)
- Memory bandwidth
- 153.6 GB/s
- FP16 (dense)
- 61.4 TFLOPS
- NPU
- Intel AI Boost NPU 5 (50 TOPS)
- Power
- 25 W max
- Released
- 2026-01-27
Intel Core Ultra X9 388H (Panther Lake) Laptop FAQ
How much memory is available for AI on the Intel Core Ultra X9 388H (Panther 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 X9 388H (Panther 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 21.9 tok/s.
Can the Intel Core Ultra X9 388H (Panther 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 X9 388H (Panther Lake) Laptop take to read a long prompt?
On Qwen3.6 35B A3B, about 3.5 s for a 4K-token prompt and 28 s for a 32K-token document before the first word appears.
Is renting a GPU cheaper than buying the Intel Core Ultra X9 388H (Panther Lake) Laptop?
An RTX 5090 (32 GB) rents from $0.46/hr.