will it local
The famous cut-down: 3GB + slower memory and fewer cores than the 6GB. Class E dead-end: the advisor says so plainly and offers the cheapest real step up instead.
This card is below the useful floor for local LLM inference — we say so plainly and point at the cheapest real step up instead.
no computed band (non-banded class)
—
no single-card bench published — band is computed (see notes)
Nominal bandwidth: — 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)
→ 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)
→ 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)
→ kokoro:82m on Tesla M60 (16GB, used) ($35) 82M · 0.3GB · needs ~2.3GB (4k ctx)
→ qwen3:4b 4B — 3.2 of 3 GB usable — barely over; real with q8 KV cache (halves KV) or shorter context
→ moondream:2b 2B — 3.7 GB vs 3 GB usable — partial CPU offload, expect large speed loss
⚠ Disambiguation trap: NOT the useful 1060 6GB; 3GB fits only 3B Q4