will it local
Same story as GT 1030 — display out only. 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 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)
→ llama3.2:1b on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) 1B · 1.3GB · needs ~1.4GB (4k ctx)
→ gemma3:1b on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) 1B · 1.0GB · needs ~1.1GB (4k ctx)
→ llama3.2:3b 3B — 2.4 GB vs 2 GB usable — partial CPU offload, expect large speed loss
→ whisper:tiny tiny — 2.1 of 2 GB usable — barely over; real with q8 KV cache (halves KV) or shorter context
→ whisper base — 2.3 GB vs 2 GB usable — partial CPU offload, expect large speed loss
→ kokoro:82m 82M — 2.3 GB vs 2 GB usable — partial CPU offload, expect large speed loss
⚠ Effectively an iGPU on a discrete board