will it local

Best local LLMs for the NVIDIA GeForce RTX 3090 Ti

Speed

computed band 90.0-150.0 tok/s for 8B Q4_K_M (roofline, 1008.0 GB/s VRAM); community: 110.0 tok/s Meta Llama 3.1 8B Instruct Q4_K_M (https://www.localscore.ai/accelerator/127); community: 64.2 tok/s Qwen2.5 14B Instruct Q4_K_M (https://www.localscore.ai/accelerator/127)

Effective decode window: 0.46–0.76 of 1008 GB/s nominal → ~464–766 GB/s effective (llama.cpp decode, Q4_K_M basis; arch window, community-calibrated)

What fits (computed)

→ 14b-q4 full 10.5 GB needed of 24 GB usable — headroom for context

→ 3b-q4 full 2.8 GB needed of 24 GB usable — headroom for context

→ 4b-q4 full 3.7 GB needed of 24 GB usable — headroom for context

→ 8b-q4 full 6.1 GB needed of 24 GB usable — headroom for context

Cited community benches (2 rows)

→ 110.0 tok/s · Meta Llama 3.1 8B Instruct Q4_K_M LocalScore median · source

→ 64.2 tok/s · Qwen2.5 14B Instruct Q4_K_M LocalScore median · source

Runs fully in memory (machine alternatives)

Nominal bandwidth: 1008.0 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 on Mac mini M4 (32GB) ($999) 27B · 16.5GB · needs ~18.5GB (4k ctx)

→ gemma3:27b on Mac mini M4 (32GB) ($999) 27B · 17GB · needs ~18.9GB (4k ctx)

→ flux:schnell on Mac mini M4 (32GB) ($999) schnell fp8 · 17GB · needs ~19GB (4k ctx)

→ qwen3:30b-a3b on Mac mini M4 (32GB) ($999) 30B-A3B MoE · 18.6GB · needs ~19GB (4k ctx)

→ qwen3-coder:30b-a3b on Mac mini M4 (32GB) ($999) 30B-A3B MoE · 18.6GB · needs ~19GB (4k ctx)

→ qwen3:32b on Mac mini M4 (32GB) ($999) 32B · 20GB · needs ~21GB (4k ctx)

→ deepseek-r1:32b on Mac mini M4 (32GB) ($999) distill 32B · 20GB · needs ~21GB (4k ctx)

→ qwen2.5vl:32b on Mac mini M5 Pro (64GB) ($1669) 32B · 22GB · needs ~23GB (4k ctx)

Borderline — runs, but offloads

→ mixtral:8x7b 8x7B MoE — 26.5 GB vs 24 GB usable — partial CPU offload, expect large speed loss

→ flux:dev dev fp8 — 25.0 of 24 GB usable — barely over; real with q8 KV cache (halves KV) or shorter context

Gotchas

⚠ Fastest Ampere: 384-bit @ 21 Gbps = 1008 GB/s, the >1TB/s club (NVIDIA spec page)

⚠ 450W card: 3x 8-pin or 12VHPWR Gen5 — PSU and case requirements are real (NVIDIA page)

⚠ 24GB = 32B Q4 full fits with room for context; used prices approach 3090 non-Ti — compare before buying

Where to go next