will it local

Best local LLMs for the NVIDIA RTX 2060

Speed

computed band 31.0-47.0 tok/s for 8B Q4_K_M (roofline, 336 GB/s VRAM); community: 35-45 tok/s 7B Q4 (kb-audit-0903)

Effective decode window: 0.48–0.72 of 336 GB/s nominal → ~161–242 GB/s effective (llama.cpp decode, Q4_K_M basis; arch window, community-calibrated)

What fits (computed)

→ 13b-q4 no 14.6 GB vs 6 GB usable — does not fit

→ 3b-q4 full 2.8 GB needed of 6 GB usable — headroom for context

→ 4b-q4 full 3.7 GB needed of 6 GB usable — headroom for context

→ 8b-q4 tight 6.1 of 6 GB usable — barely over; real with q8 KV cache (halves KV) or shorter context

Cited community benches (1 rows)

→ 35-45 tok/s · 7B Q4 scaled from 2060 Super measured 52.8-62.5 8B by bandwidth ratio · kb-audit-0903

Runs fully in memory (machine alternatives)

Nominal bandwidth: 336 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)

→ 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)

Borderline — runs, but offloads

→ llava:7b 7B — 6.7 GB vs 6 GB usable — partial CPU offload, expect large speed loss

Gotchas

⚠ Build llama.cpp with CMAKE_CUDA_ARCHITECTURES=75 or silently lose ~19% to PTX JIT

⚠ 6GB forces context discipline (-c 4096 class)

⚠ Tensor cores help prefill; decode stays bandwidth-bound

Where to go next