local intelligence

will it local

Best local LLMs for the NVIDIA GeForce RTX 3080 Ti

12GB · Ampere

12GB GDDR6X, 384-bit @ 19 Gbps = 912.4 GB/s (videocardz final-spec confirmation) Alias-class to 3080 12GB in LLM terms — identical memory subsystem MSRP-era mining-card warning applies to used units (fan/thermal wear)

explore the full catalogupgrade paths with live prices · what fits on each machine

Speed

computed band 82.0-130.0 tok/s for 8B Q4_K_M (roofline, 912.4 GB/s VRAM); community: 87.1 tok/s Meta Llama 3.1 8B Instruct Q4_K_M (https://www.localscore.ai/accelerator/120); community: 46.1 tok/s Qwen2.5 14B Instruct Q4_K_M (https://www.localscore.ai/accelerator/120)

Effective decode window: 0.46–0.76 of 912.4 GB/s nominal → ~420–693 GB/s effective (llama.cpp decode, Q4_K_M basis; arch window, community-calibrated)

What fits (computed)

14b-q4 tight 10.5 of 12 GB usable — keep context modest

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

Cited community benches (2 rows)

→ 87.1 tok/s · Meta Llama 3.1 8B Instruct Q4_K_M LocalScore median · source

→ 46.1 tok/s · Qwen2.5 14B Instruct Q4_K_M LocalScore median · source

Runs fully in memory (machine alternatives)

Nominal bandwidth: 912.4 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)

Borderline — runs, but offloads

→ gpt-oss:20b 20B MoE — 14.2 GB vs 12 GB usable — partial CPU offload, expect large speed loss

Gotchas

⚠ 12GB GDDR6X, 384-bit @ 19 Gbps = 912.4 GB/s (videocardz final-spec confirmation)

⚠ Alias-class to 3080 12GB in LLM terms — identical memory subsystem

⚠ MSRP-era mining-card warning applies to used units (fan/thermal wear)

Where to go next

rtx-3090

24GB unlocks 32B Q4 full fits (rtx-3090 card in KB)

→ its best-models page

2026-09-18 · ← full hardware catalog · fit = working set vs VRAM · speeds are community-reported, cited in our knowledge base