Apple M1 Ultra (64 GB)

Apple M1

Unified memory: 64 GB
Memory bandwidth: 800 GB/s
Class: Apple

Figures assume the 64 GB unified memory pool shared between CPU and GPU. "What runs on it" is judged at a 8,192-token context. Speeds are estimates, not measurements.

What runs on it

Model	Sweet-spot quant	Est. speed	Community
DeepSeek-R1-Distill-Llama-8B deepseek-ai	Q4_K_M Runs fully on GPU @ 8K ctx	80–107 tok/s (estimate)	no community data
DeepSeek-R1-Distill-Qwen-1.5B deepseek-ai	Q4_K_M Runs fully on GPU @ 8K ctx	355–473 tok/s (estimate)	no community data
DeepSeek-R1-Distill-Qwen-14B deepseek-ai	Q4_K_M Runs fully on GPU @ 8K ctx	45–60 tok/s (estimate)	no community data
DeepSeek-R1-Distill-Qwen-32B deepseek-ai	Q4_K_M Runs fully on GPU @ 8K ctx	22–29 tok/s (estimate)	no community data
DeepSeek-R1-Distill-Qwen-7B deepseek-ai	Q4_K_M Runs fully on GPU @ 8K ctx	93–124 tok/s (estimate)	no community data
Mistral-Small-3.2-24B-Instruct-2506 mistralai	Q4_K_M Runs fully on GPU @ 8K ctx	33–45 tok/s (estimate)	no community data
Qwen2.5-7B-Instruct Qwen	Q4_K_M Runs fully on GPU @ 8K ctx	44–58 tok/s (estimate)	no community data
Qwen3-30B-A3B-Instruct-2507 Qwen	Q4_K_M Runs fully on GPU @ 8K ctx	169–225 tok/s (estimate)	no community data
Qwen3-32B Qwen	Q4_K_M Runs fully on GPU @ 8K ctx	22–29 tok/s (estimate)	no community data
Qwen3-8B Qwen	Q4_K_M Runs fully on GPU @ 8K ctx	77–103 tok/s (estimate)	no community data
Qwen3-Coder-30B-A3B-Instruct Qwen	Q4_K_M Runs fully on GPU @ 8K ctx	169–225 tok/s (estimate)	no community data
Qwen3.6-27B Qwen	Q4_K_M Runs fully on GPU @ 8K ctx	25–34 tok/s (estimate)	no community data
Qwen3.6-35B-A3B Qwen	Q4_K_M Runs fully on GPU @ 8K ctx	21–28 tok/s (estimate)	no community data
gemma-4-12B-it google	Q4_K_M Runs fully on GPU @ 8K ctx	67–90 tok/s (estimate)	no community data
gemma-4-26B-A4B-it google	Q4_K_M Runs fully on GPU @ 8K ctx	25–34 tok/s (estimate)	no community data
gemma-4-31B-it google	Q4_K_M Runs fully on GPU @ 8K ctx	26–35 tok/s (estimate)	no community data
gemma-4-E2B-it google	Q4_K_M Runs fully on GPU @ 8K ctx	155–206 tok/s (estimate)	no community data
gemma-4-E4B-it google	Q4_K_M Runs fully on GPU @ 8K ctx	96–129 tok/s (estimate)	no community data
gpt-oss-20b openai	F16 Runs fully on GPU @ 8K ctx	138–184 tok/s (estimate)	no community data

"Est. speed" is a modelled range labelled estimate (D8) for generation (decode) throughput. "Community" shows the median of approved user-submitted reports on this GPU class only where enough exist — never an estimate. "pp" is measured prompt-processing (ingestion) throughput from approved community reports; rows without a measurement show none.