local intelligence

will it local

Best local LLMs for the NVIDIA Tesla M60

16GB · Maxwell

Two Maxwell half-cards for ~$35: cheap, hot, and bottom-tier — but it still runs today's stack (slowly). For about double, the P100 brings HBM2 and 4.5× the bandwidth.

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

Speed

computed band 8.7-16.0 tok/s for 8B Q4_K_M (roofline, 160.4 GB/s VRAM)

Effective decode window: 0.28–0.50 of 160.4 GB/s nominal → ~45–80 GB/s effective (llama.cpp decode, Q4_K_M basis; arch window, community-calibrated)

What fits (computed)

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

Cited community benches

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

Runs fully in memory (machine alternatives)

Nominal bandwidth: 160.4 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)

Borderline — runs, but offloads

→ 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

Gotchas

⚠ Dual-GPU card: 2×8GB halves — each shard must fit 8GB; layers split across the pair

⚠ Ancient Maxwell (2015): pre-tensor, hot, loud — the 'old, slow' tier

⚠ Passive cooling, 300W — server airflow required; no display outputs

⚠ No community 8B bench row cited — band computed

Where to go next

Tesla P100 (16GB, used)

$80 — ~$80 for 4.5× the bandwidth (HBM2)

eBay (used) ↗ · Amazon ↗

Tesla P40 (24GB, used)

$270 — 24GB Pascal for real serving

eBay (used) ↗ · Amazon ↗

2026-09-20 · ← full hardware catalog · fit = working set vs VRAM · speeds are community-reported, cited in our knowledge base