will it local

Best local LLMs for the Intel Lunar Lake (Core Ultra 200V)

Shared-memory device — speed scales with RAM bandwidth (136.5 GB/s shared RAM), usable for inference ≈ 14.0 GB of 16 GB system RAM

Speed

computed band 12.0-19.0 tok/s for 8B Q4_K_M (roofline, 136.5 GB/s shared RAM); evidence pass 0917: 0.61-0.68 implied across three engine paths (single-device, low n)

Effective decode window: 0.45–0.70 of 136.5 GB/s nominal → ~61–96 GB/s effective (llama.cpp decode, Q4_K_M basis; arch window, community-calibrated; nominal is LPDDR/JEDEC channel arithmetic (shared memory))

What fits (computed)

→ 13b-q4 tight 14.6 of 14 GB usable — barely over; real with q8 KV cache (halves KV) or shorter context

→ 3b-q4 full 2.8 GB needed of 14 GB usable — headroom for context

→ 4b-q4 full 3.7 GB needed of 14 GB usable — headroom for context

→ 8b-q4 full 6.1 GB needed of 14 GB usable — headroom for context

Cited community benches

no single-card bench published — band is computed (see notes)

Runs fully in memory (machine alternatives)

Nominal bandwidth: 136.5 GB/s shared memory — see the effective decode window above

→ qwen3:0.6b on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) 0.6B · 0.6GB · needs ~1GB (4k ctx)

→ qwen3:1.7b on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) 1.7B · 1.4GB · needs ~1.8GB (4k ctx)

→ qwen3:4b on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) 4B · 2.6GB · needs ~3.2GB (4k ctx)

→ llama3.2:1b on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) 1B · 1.3GB · needs ~1.4GB (4k ctx)

→ llama3.2:3b on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) 3B · 2.0GB · needs ~2.4GB (4k ctx)

→ gemma3:1b on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) 1B · 1.0GB · needs ~1.1GB (4k ctx)

→ phi4:mini on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) mini 3.8B · 2.5GB · needs ~3GB (4k ctx)

→ moondream:2b on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) 2B · 1.7GB · needs ~3.7GB (4k ctx)

→ whisper:tiny on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) tiny · 0.1GB · needs ~2.1GB (4k ctx)

→ whisper on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) base · 0.3GB · needs ~2.3GB (4k ctx)

→ whisper:small on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) small · 0.9GB · needs ~2.9GB (4k ctx)

→ whisper:medium on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) medium · 3.1GB · needs ~5.1GB (4k ctx)

→ kokoro:82m on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) 82M · 0.3GB · needs ~2.3GB (4k ctx)

→ gemma3:4b on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) 4B · 3.3GB · needs ~3.8GB (4k ctx)

→ deepseek-r1:7b on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) distill 7B · 4.7GB · needs ~4.9GB (4k ctx)

→ mistral:7b on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) 7B · 4.1GB · needs ~4.6GB (4k ctx)

→ llava:7b on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) 7B · 4.7GB · needs ~6.7GB (4k ctx)

→ qwen3:8b on Tesla P100 (16GB, used) ($135) 8B · 5.2GB · needs ~5.8GB (4k ctx)

→ qwen2.5vl:7b on Tesla P100 (16GB, used) ($135) 7B · 5.6GB · needs ~5.8GB (4k ctx)

→ llama3.1:8b on Tesla P100 (16GB, used) ($135) 8B · 4.9GB · needs ~5.4GB (4k ctx)

→ deepseek-r1:8b on Tesla P100 (16GB, used) ($135) distill 8B · 4.9GB · needs ~5.4GB (4k ctx)

→ whisper:large-v3 on Tesla P100 (16GB, used) ($135) large-v3 · 6.2GB · needs ~8.2GB (4k ctx)

→ mistral-nemo:12b on Tesla P100 (16GB, used) ($135) 12B · 7.1GB · needs ~7.7GB (4k ctx)

→ sdxl on Tesla P100 (16GB, used) ($135) SDXL base · 6.9GB · needs ~8.9GB (4k ctx)

→ llava:13b on Tesla P100 (16GB, used) ($135) 13B · 8.0GB · needs ~11.1GB (4k ctx)

→ gemma3:12b on Tesla P100 (16GB, used) ($135) 12B · 8.1GB · needs ~9.6GB (4k ctx)

→ qwen3:14b on Tesla P100 (16GB, used) ($135) 14B · 9.3GB · needs ~9.9GB (4k ctx)

→ deepseek-r1:14b on Tesla P100 (16GB, used) ($135) distill 14B · 9.0GB · needs ~9.8GB (4k ctx)

→ phi4:14b on Tesla P100 (16GB, used) ($135) 14B · 9.1GB · needs ~9.9GB (4k ctx)

Borderline — runs, but offloads

→ gpt-oss:20b 20B MoE — 14.2 of 14 GB usable — barely over; real with q8 KV cache (halves KV) or shorter context

→ devstral:24b 24B — 15.2 GB vs 14 GB usable — partial CPU offload, expect large speed loss

Gotchas

⚠ 136.5 GB/s on-package LPDDR5X-8533 (16/32GB fixed — no upgrades, ever)

⚠ Xe2 iGPU + SYCL/Vulkan: 8B Q4 ~9-13 tok/s; NPU (48 TOPS) not usable by llama.cpp for decode

⚠ RAM soldered at purchase — pick 32GB if 14B-class is the goal

Where to go next

—