will it local
The default first local-LLM card for a reason: 12GB for used-market money, runs everything through 14B properly. AVOID the 6GB 3060 variant for LLMs entirely.
computed band 39.0-62.0 tok/s for 8B Q4_K_M (roofline, 360 GB/s VRAM); community: 51.6 tok/s 8B Q4_K_M (https://www.localscore.ai); community: 26.4 tok/s 14B Q4 (https://www.localscore.ai); community: 60.2 tok/s 7B Q4 (kb-audit-0903)
Effective decode window: 0.55–0.88 of 360 GB/s nominal → ~198–317 GB/s effective (llama.cpp decode, Q4_K_M basis; arch window, community-calibrated)
Community check — localmaxxing.com medians (4 buckets): localmaxxing.com
→ ~76 tok/s · 3-4B Q4 · 88 runs · just below our band (1% under the low edge)
→ ~150 tok/s · 3-4B Q8 · 3 runs · above our band — small sample; documented outlier, computed window stands
→ ~49 tok/s · 8-9B Q4 · 85 runs · inside our computed band
→ ~32 tok/s · 12-15B Q4 · 12 runs · inside our computed band
→ 13b-q4 offload-partial 14.6 GB vs 12 GB usable — partial CPU offload, expect large speed loss
→ 3b-q4 full 2.8 GB needed of 12 GB usable — headroom for context
→ 4b-q4 full 3.7 GB needed of 12 GB usable — headroom for context
→ 8b-q4 full 6.1 GB needed of 12 GB usable — headroom for context
→ 51.6 tok/s · 8B Q4_K_M LocalScore · source
→ 26.4 tok/s · 14B Q4 LocalScore · source
→ 60.2 tok/s · 7B Q4 Vulkan (geerlingguy) · kb-audit-0903
Nominal bandwidth: 360 GB/s — 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)
→ gpt-oss:20b 20B MoE — 14.2 GB vs 12 GB usable — partial CPU offload, expect large speed loss
⚠ AVOID the 6GB 3060 variant for LLMs entirely — same name, half the memory
⚠ Ampere: full CUDA + tensor-core support, no caveats
$1100 — 24GB used: 32B Q4 fully resident, the serious tier
$3499 — unified memory path: silent, efficient, 36GB+ class