will it local
GB206, 4608 CUDA, 128-bit GDDR7 at 28 Gbps = 448 GB/s (TechPowerUp, live-pinned 0905). Budget 16GB entry: fit profile of a 4060 Ti 16GB at Blackwell efficiency, half the feed rate of higher tiers.
computed band 40.0-66.0 tok/s for 8B Q4_K_M (roofline, 448.0 GB/s VRAM); community: 59.0 tok/s Meta Llama 3.1 8B Instruct Q4_K_M (https://www.localscore.ai/accelerator/860); community: 42 tok/s Llama 3.1 8B Q4_K_M (https://www.compute-market.com/blog/rx-9070-xt-vs-rtx-5060-ti-local-ai-2026)
Effective decode window: 0.46–0.76 of 448 GB/s nominal → ~206–340 GB/s effective (llama.cpp decode, Q4_K_M basis; arch window, community-calibrated)
→ 13b-q4 tight 14.6 of 16 GB usable — keep context modest
→ 3b-q4 full 2.8 GB needed of 16 GB usable — headroom for context
→ 4b-q4 full 3.7 GB needed of 16 GB usable — headroom for context
→ 8b-q4 full 6.1 GB needed of 16 GB usable — headroom for context
→ 59.0 tok/s · Meta Llama 3.1 8B Instruct Q4_K_M LocalScore median · source
→ 42 tok/s · Llama 3.1 8B Q4_K_M Compute Market 2026 ROCm-vs-CUDA roundup (CUDA) · source
Nominal bandwidth: 448.0 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 on Tesla P40 (24GB, used) ($290) 20B MoE · 14GB · needs ~14.2GB (4k ctx)
→ devstral:24b on Tesla P40 (24GB, used) ($290) 24B · 14.6GB · needs ~15.2GB (4k ctx)
→ qwen3.8:27b 27B — 18.5 GB vs 16 GB usable — partial CPU offload, expect large speed loss
→ qwen3:30b-a3b 30B-A3B MoE — 19.0 GB vs 16 GB usable — partial CPU offload, expect large speed loss
→ qwen3-coder:30b-a3b 30B-A3B MoE — 19.0 GB vs 16 GB usable — partial CPU offload, expect large speed loss
→ gemma3:27b 27B — 18.9 GB vs 16 GB usable — partial CPU offload, expect large speed loss
→ flux:schnell schnell fp8 — 19.0 GB vs 16 GB usable — partial CPU offload, expect large speed loss
⚠ VRAM-rich, bandwidth-poor: 16GB but only 448 GB/s on a 128-bit bus — fits 14B Q4 and feeds it at half a 5070 Ti's rate
⚠ The 8GB 5060 Ti is the mass-market card and is NOT this card: 8GB cannot hold 14B Q4 — buy the 16GB variant specifically
⚠ LocalScore 8B median 59.0 inside community 42-64 spread — arch window holds, no override needed
⚠ 180W, single 8-pin — the easiest 50-series card to house
$900 — 2× the bandwidth, same 16GB — the same-VRAM step up