will it local
The efficient one: 70W single-slot Turing that every current stack supports. You pay for the form factor — ~$450 used for 16GB, when the 24GB P40 sits near $270 and the V100 16GB near $245.
computed band 30.0-45.0 tok/s for 8B Q4_K_M (roofline, 320.0 GB/s VRAM)
Effective decode window: 0.48–0.72 of 320 GB/s nominal → ~154–230 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
no single-card bench published — band is computed (see notes)
Nominal bandwidth: 320.0 GB/s — see the effective decode window above
→ qwen3:0.6b on Tesla M60 (16GB, used) ($35) 0.6B · 0.6GB · needs ~1GB (4k ctx)
→ qwen3:1.7b on Tesla M60 (16GB, used) ($35) 1.7B · 1.4GB · needs ~1.8GB (4k ctx)
→ qwen3:4b on Tesla M60 (16GB, used) ($35) 4B · 2.6GB · needs ~3.2GB (4k ctx)
→ llama3.2:1b on Tesla M60 (16GB, used) ($35) 1B · 1.3GB · needs ~1.4GB (4k ctx)
→ llama3.2:3b on Tesla M60 (16GB, used) ($35) 3B · 2.0GB · needs ~2.4GB (4k ctx)
→ gemma3:1b on Tesla M60 (16GB, used) ($35) 1B · 1.0GB · needs ~1.1GB (4k ctx)
→ phi4:mini on Tesla M60 (16GB, used) ($35) mini 3.8B · 2.5GB · needs ~3GB (4k ctx)
→ moondream:2b on Tesla M60 (16GB, used) ($35) 2B · 1.7GB · needs ~3.7GB (4k ctx)
→ whisper:tiny on Tesla M60 (16GB, used) ($35) tiny · 0.1GB · needs ~2.1GB (4k ctx)
→ whisper on Tesla M60 (16GB, used) ($35) base · 0.3GB · needs ~2.3GB (4k ctx)
→ whisper:small on Tesla M60 (16GB, used) ($35) small · 0.9GB · needs ~2.9GB (4k ctx)
→ whisper:medium on Tesla M60 (16GB, used) ($35) medium · 3.1GB · needs ~5.1GB (4k ctx)
→ kokoro:82m on Tesla M60 (16GB, used) ($35) 82M · 0.3GB · needs ~2.3GB (4k ctx)
→ gemma3:4b on Tesla M60 (16GB, used) ($35) 4B · 3.3GB · needs ~3.8GB (4k ctx)
→ deepseek-r1:7b on Tesla M60 (16GB, used) ($35) distill 7B · 4.7GB · needs ~4.9GB (4k ctx)
→ mistral:7b on Tesla M60 (16GB, used) ($35) 7B · 4.1GB · needs ~4.6GB (4k ctx)
→ llava:7b on Tesla M60 (16GB, used) ($35) 7B · 4.7GB · needs ~6.7GB (4k ctx)
→ qwen3:8b on Tesla M60 (16GB, used) ($35) 8B · 5.2GB · needs ~5.8GB (4k ctx)
→ qwen2.5vl:7b on Tesla M60 (16GB, used) ($35) 7B · 5.6GB · needs ~5.8GB (4k ctx)
→ llama3.1:8b on Tesla M60 (16GB, used) ($35) 8B · 4.9GB · needs ~5.4GB (4k ctx)
→ deepseek-r1:8b on Tesla M60 (16GB, used) ($35) distill 8B · 4.9GB · needs ~5.4GB (4k ctx)
→ whisper:large-v3 on Tesla M60 (16GB, used) ($35) large-v3 · 6.2GB · needs ~8.2GB (4k ctx)
→ mistral-nemo:12b on Tesla M60 (16GB, used) ($35) 12B · 7.1GB · needs ~7.7GB (4k ctx)
→ sdxl on Tesla M60 (16GB, used) ($35) SDXL base · 6.9GB · needs ~8.9GB (4k ctx)
→ llava:13b on Tesla M60 (16GB, used) ($35) 13B · 8.0GB · needs ~11.1GB (4k ctx)
→ gemma3:12b on Tesla M60 (16GB, used) ($35) 12B · 8.1GB · needs ~9.6GB (4k ctx)
→ qwen3:14b on Tesla M60 (16GB, used) ($35) 14B · 9.3GB · needs ~9.9GB (4k ctx)
→ deepseek-r1:14b on Tesla M60 (16GB, used) ($35) distill 14B · 9.0GB · needs ~9.8GB (4k ctx)
→ phi4:14b on Tesla M60 (16GB, used) ($35) 14B · 9.1GB · needs ~9.9GB (4k ctx)
→ gpt-oss:20b on Tesla M40 (24GB, used) ($55) 20B MoE · 14GB · needs ~14.2GB (4k ctx)
→ devstral:24b on Tesla M40 (24GB, used) ($55) 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
⚠ The modern-stack pick: Turing (compute 7.5) — zero era caveats, unlike every other cheap pull
⚠ 70W, single-slot, slot-powered — but passive: server-style airflow still required
⚠ 320 GB/s GDDR6 caps decode — an 8B-class card that still sips power
⚠ No community 8B bench row cited — band computed
$245 — faster and usually cheaper used — needs the watts and a shroud