local intelligence

will it local

Best local LLMs for the GTX 1650 Mobile

4GB · Turing TU117

Turing TU117 without tensor cores — dp4a kernels only 4GB: 3B/4B Q4 full, 8B Q4 offloads GDDR6 variant of 1650 exists on desktop — mobile is GDDR5 128.1 GB/s

⚠ Laptop part — mobile clocks and thermals run below desktop sibling speeds; treat the band as optimistic for sustained load.

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

Speed

computed band 12.0-18.0 tok/s for 8B Q4_K_M (roofline, 128.1 GB/s VRAM)

Effective decode window: 0.48–0.72 of 128.1 GB/s nominal → ~61–92 GB/s effective (llama.cpp decode, Q4_K_M basis; arch window, community-calibrated)

What fits (computed)

13b-q4 no 14.6 GB vs 4 GB usable — does not fit

3b-q4 full 2.8 GB needed of 4 GB usable — headroom for context

4b-q4 tight 3.7 of 4 GB usable — keep context modest

8b-q4 no 6.1 GB vs 4 GB usable — does not fit

Cited community benches

no single-card bench published — band is computed (see notes)

Runs fully in memory (machine alternatives)

Nominal bandwidth: 128.1 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)

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)

Borderline — runs, but offloads

→ deepseek-r1:7b distill 7B — 4.9 GB vs 4 GB usable — partial CPU offload, expect large speed loss

→ mistral:7b 7B — 4.6 GB vs 4 GB usable — partial CPU offload, expect large speed loss

Gotchas

⚠ Turing TU117 without tensor cores — dp4a kernels only

⚠ 4GB: 3B/4B Q4 full, 8B Q4 offloads

⚠ GDDR6 variant of 1650 exists on desktop — mobile is GDDR5 128.1 GB/s

Where to go next

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