will it local
Best $/VRAM in the used market (32GB HBM2) but you live on Vulkan or frozen ROCm. No CUDA. Great second/third card in a Linux box; painful as a primary.
computed band 56.0-90.0 tok/s for 8B Q4_K_M (roofline, 1024 GB/s VRAM); community: 12.9 tok/s Qwen2.5 14B Instruct Q4_K_M (https://www.localscore.ai/accelerator/1285)
Effective decode window: 0.28–0.45 of 1024 GB/s nominal → ~287–461 GB/s effective (llama.cpp decode, Q4_K_M basis; arch window, community-calibrated)
→ 13b-q4 full 14.6 GB needed of 32 GB usable — headroom for context
→ 3b-q4 full 2.8 GB needed of 32 GB usable — headroom for context
→ 4b-q4 full 3.7 GB needed of 32 GB usable — headroom for context
→ 8b-q4 full 6.1 GB needed of 32 GB usable — headroom for context
→ 12.9 tok/s · Qwen2.5 14B Instruct Q4_K_M llamafile (LocalScore) · source
Nominal bandwidth: 1024 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)
→ whisper:medium on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) medium · 3.1GB · needs ~5.1GB (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)
→ deepseek-r1:7b on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) distill 7B · 4.7GB · needs ~4.9GB (4k ctx)
→ mistral:7b on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) 7B · 4.1GB · needs ~4.6GB (4k ctx)
→ llava:7b on Raspberry Pi 5 + AI Kit (Hailo-8L) ($110) 7B · 4.7GB · needs ~6.7GB (4k ctx)
→ qwen3:8b on Tesla P100 (16GB, used) ($135) 8B · 5.2GB · needs ~5.8GB (4k ctx)
→ qwen2.5vl:7b on Tesla P100 (16GB, used) ($135) 7B · 5.6GB · needs ~5.8GB (4k ctx)
→ llama3.1:8b on Tesla P100 (16GB, used) ($135) 8B · 4.9GB · needs ~5.4GB (4k ctx)
→ deepseek-r1:8b on Tesla P100 (16GB, used) ($135) distill 8B · 4.9GB · needs ~5.4GB (4k ctx)
→ whisper:large-v3 on Tesla P100 (16GB, used) ($135) large-v3 · 6.2GB · needs ~8.2GB (4k ctx)
→ mistral-nemo:12b on Tesla P100 (16GB, used) ($135) 12B · 7.1GB · needs ~7.7GB (4k ctx)
→ sdxl on Tesla P100 (16GB, used) ($135) SDXL base · 6.9GB · needs ~8.9GB (4k ctx)
→ llava:13b on Tesla P100 (16GB, used) ($135) 13B · 8.0GB · needs ~11.1GB (4k ctx)
→ gemma3:12b on Tesla P100 (16GB, used) ($135) 12B · 8.1GB · needs ~9.6GB (4k ctx)
→ qwen3:14b on Tesla P100 (16GB, used) ($135) 14B · 9.3GB · needs ~9.9GB (4k ctx)
→ deepseek-r1:14b on Tesla P100 (16GB, used) ($135) distill 14B · 9.0GB · needs ~9.8GB (4k ctx)
→ phi4:14b on Tesla P100 (16GB, used) ($135) 14B · 9.1GB · needs ~9.9GB (4k ctx)
→ gpt-oss:20b on Tesla P40 (24GB, used) ($290) 20B MoE · 14GB · needs ~14.2GB (4k ctx)
→ devstral:24b on Tesla P40 (24GB, used) ($290) 24B · 14.6GB · needs ~15.2GB (4k ctx)
→ qwen3.8:27b on Mac mini M4 (32GB) ($999) 27B · 16.5GB · needs ~18.5GB (4k ctx)
→ gemma3:27b on Mac mini M4 (32GB) ($999) 27B · 17GB · needs ~18.9GB (4k ctx)
→ flux:schnell on Mac mini M4 (32GB) ($999) schnell fp8 · 17GB · needs ~19GB (4k ctx)
→ qwen3:30b-a3b on Mac mini M4 (32GB) ($999) 30B-A3B MoE · 18.6GB · needs ~19GB (4k ctx)
→ qwen3-coder:30b-a3b on Mac mini M4 (32GB) ($999) 30B-A3B MoE · 18.6GB · needs ~19GB (4k ctx)
→ qwen3:32b on Mac mini M4 (32GB) ($999) 32B · 20GB · needs ~21GB (4k ctx)
→ deepseek-r1:32b on Mac mini M4 (32GB) ($999) distill 32B · 20GB · needs ~21GB (4k ctx)
→ qwen2.5vl:32b on Mac mini M5 Pro (64GB) ($1669) 32B · 22GB · needs ~23GB (4k ctx)
→ flux:dev on Mac mini M5 Pro (64GB) ($1669) dev fp8 · 23GB · needs ~25GB (4k ctx)
→ mixtral:8x7b on Mac mini M5 Pro (64GB) ($1669) 8x7B MoE · 26GB · needs ~26.5GB (4k ctx)
—
⚠ ROCm has sunset gfx906: MI50/MI60 are deprecated/being removed from current ROCm releases - you must pin old ROCm versions (Linux only).
⚠ Vulkan (RADV) + llama.cpp is the maintenance-free path and works well, but no CUDA: mainstream vLLM and most fine-tune stacks are off the table.
⚠ Passive dual-slot server card, 300W, 2x 8-pin, no display outputs - needs forced airflow and a beefy PSU.
⚠ The 32GB MI50 is a server-pull variant - AMD's launch SKUs were MI50 16GB / MI60 32GB; only one LocalScore row exists (Qwen2.5-14B Q4_K_M 12.9 tok/s on the combined MI50/MI60 16GB page), no Llama 3.1 8B bench.