← CanIRunLocal · All hardware · All models
Alibaba · 125B parameters (10B active) · chat, reasoning, coding, vision.
Ollama weight files: Q4_K_M 81 GB (qwen3.5:122b).
Yes on 18 machines in this list. The smallest is Mac Studio M3 Ultra 96GB: Q4_K_M, about 83.7 GB, roughly 51 tokens per second, via Ollama. ollama run qwen3.5:122b
ollama run qwen3.5:122bollama run qwen3.5:122bollama run qwen3.5:122bollama run qwen3.5:122blms get unsloth/Qwen3.5-122B-A10B-GGUF@Q5_K_Mllama-server -hf unsloth/Qwen3.5-122B-A10B-GGUF:Q5_K_M -c 8192vllm serve Qwen/Qwen3.5-122B-A10B-GPTQ-Int4 --max-model-len 8192 --gpu-memory-utilization 0.9| Hardware | Runtime | Quant | Memory | Fit | Speed | Command |
|---|---|---|---|---|---|---|
| Mac Studio M3 Ultra 96GB | Ollama | Q4_K_M | 83.7 GB | fits if the Mac GPU limit is raised | ~51 tok/s | ollama run qwen3.5:122b |
| Mac Studio M5 Ultra 96GB | Ollama | Q4_K_M | 83.7 GB | fits if the Mac GPU limit is raised | ~74 tok/s | ollama run qwen3.5:122b |
| M3 Max 128GB | Ollama | Q4_K_M | 83.7 GB | fits in fast memory | ~25 tok/s | ollama run qwen3.5:122b |
| M4 Max 128GB | Ollama | Q4_K_M | 83.7 GB | fits in fast memory | ~34 tok/s | ollama run qwen3.5:122b |
| Mac Studio M4 Max (40c GPU) 128GB | Ollama | Q4_K_M | 83.7 GB | fits in fast memory | ~34 tok/s | ollama run qwen3.5:122b |
| Mac Studio M5 Max (40c GPU) 128GB | Ollama | Q4_K_M | 83.7 GB | fits in fast memory | ~38 tok/s | ollama run qwen3.5:122b |
| DGX Spark 128GB (NVIDIA, ASUS, Dell, Lenovo, HP, MSI, Acer, Gigabyte) | Ollama | Q4_K_M | 83.7 GB | fits in fast memory | ~24 tok/s | ollama run qwen3.5:122b |
| M2 Ultra 192GB | Ollama | Q4_K_M | 83.7 GB | fits in fast memory | ~49 tok/s | ollama run qwen3.5:122b |
| 2x Mac Studio M5 Max (40c GPU) 128GB | llama.cpp | Q8_0 GGUF | 132.6 GB | fits in fast memory | ~20 tok/s | llama-server -hf unsloth/Qwen3.5-122B-A10B-GGUF:Q8_0 --rpc node2:50052 -c 8192 # run rpc-server on each other node |
| Mac Studio M3 Ultra 256GB | Ollama | Q4_K_M | 83.7 GB | fits in fast memory | ~51 tok/s | ollama run qwen3.5:122b |
| Mac Studio M5 Ultra (64c GPU) 256GB | Ollama | Q4_K_M | 83.7 GB | fits in fast memory | ~74 tok/s | ollama run qwen3.5:122b |
| Mac Studio M5 Ultra (80c GPU) 256GB | Ollama | Q4_K_M | 83.7 GB | fits in fast memory | ~74 tok/s | ollama run qwen3.5:122b |
| 2x DGX Spark 128GB | llama.cpp | Q8_0 GGUF | 132.6 GB | fits in fast memory | ~13 tok/s | llama-server -hf unsloth/Qwen3.5-122B-A10B-GGUF:Q8_0 --rpc node2:50052 -c 8192 # run rpc-server on each other node |
| 4x Mac Studio M5 Max (40c GPU) 128GB | llama.cpp | Q8_0 GGUF | 132.6 GB | fits in fast memory | ~18 tok/s | llama-server -hf unsloth/Qwen3.5-122B-A10B-GGUF:Q8_0 --rpc node2:50052,node3:50052,node4:50052 -c 8192 # run rpc-server on each other node |
| 2x Mac Studio M5 Ultra (80c GPU) 256GB | llama.cpp | Q8_0 GGUF | 132.6 GB | fits in fast memory | ~39 tok/s | llama-server -hf unsloth/Qwen3.5-122B-A10B-GGUF:Q8_0 --rpc node2:50052 -c 8192 # run rpc-server on each other node |
| Mac Studio M3 Ultra (80c GPU) 512GB | Ollama | Q4_K_M | 83.7 GB | fits in fast memory | ~51 tok/s | ollama run qwen3.5:122b |
| 4x DGX Spark 128GB | llama.cpp | Q8_0 GGUF | 132.6 GB | fits in fast memory | ~11 tok/s | llama-server -hf unsloth/Qwen3.5-122B-A10B-GGUF:Q8_0 --rpc node2:50052,node3:50052,node4:50052 -c 8192 # run rpc-server on each other node |
| 4x Mac Studio M5 Ultra (80c GPU) 256GB | llama.cpp | Q8_0 GGUF | 132.6 GB | fits in fast memory | ~35 tok/s | llama-server -hf unsloth/Qwen3.5-122B-A10B-GGUF:Q8_0 --rpc node2:50052,node3:50052,node4:50052 -c 8192 # run rpc-server on each other node |
Estimates, not benchmarks. Model sizes are ollama.com download sizes; memory needed adds headroom for ~8k tokens of context; speeds are rough figures from memory bandwidth. Data updated 2026-10-18.
A project by OnDevice Labs · llms.txt