Appearance
Explore LLM, image and video benchmark results for Mac Studio (M5 Max), with hardware specifications and the software settings used in each test.
| Model | Benchmark | Configuration | Mac Studio M5 Max | Olares One |
|---|---|---|---|---|
| Qwen3.8-27B | IFBench Evaluation time | Ollama (MLX), nvfp4 | 12.2 h | 8.7 h |
| Qwen3.8-27B | GPQA Diamond Evaluation time | Ollama (MLX), nvfp4 | 14.9 h | 11.5 h |
| Qwen3.8-27B | Inference speed Token generation, single request | Ollama (MLX), nvfp4 | 74 tok/s | 93 tok/s |
| Qwen3.8-Flash-Next | Inference speed Token generation, single request | Strata, Q2_0 | 130 tok/s | 166 tok/s |
| Qwen-Image-2.1 Base | Text to image Per image | ComfyUI, int8, --gpu-only | 1.6 min | 12 s |
| Qwen-Image-2.1 Base | Image edit Per image | ComfyUI, int8, --gpu-only | 1.9 min | 17 s |
| Qwen-Image-2.1 Turbo | Image edit Per image | ComfyUI, int8, --gpu-only | 30 s | 5.2 s |
| MiniMax H3 FastH3 v2 | Text to video Sampling time 720p, 5 s | ComfyUI, nvfp4 | 11 min | 78 s |
Ollama (MLX), nvfp4
OLLAMA_CONTEXT_LENGTH=100352 OLLAMA_HOST=http://0.0.0.0:11434 OLLAMA_KEEP_ALIVE=30m0s OLLAMA_NUM_PARALLEL=1 OLLAMA_FLASH_ATTENTION=falseOllama (MLX), nvfp4
OLLAMA_CONTEXT_LENGTH=100352 OLLAMA_HOST=0.0.0.0:11434 OLLAMA_KEEP_ALIVE=30m OLLAMA_NUM_PARALLEL=1 OLLAMA_FLASH_ATTENTION=FalseOllama (MLX), nvfp4
OLLAMA_HOST=0.0.0.0:11434 OLLAMA_NUM_PARALLEL=4 OLLAMA_KEEP_ALIVE=30m OLLAMA_NO_CLOUD=0 OLLAMA_CONTEXT_LENGTH=100352Ollama (GGML), UD-Q4_K_XL
OLLAMA_HOST=0.0.0.0:11434 OLLAMA_NUM_PARALLEL=4 OLLAMA_KEEP_ALIVE=30m OLLAMA_NO_CLOUD=0 OLLAMA_CONTEXT_LENGTH=100352Strata, Q2_0
--pack q2_0 --native Qwen3.8-Flash-Next-GSQ-RCO-Q2_0-00001-of-00002.gguf --ple-gguf Qwen3.8-Flash-Next-GSQ-RCO-Q2_0-00002-of-00002.gguf --expert-profile expert-profile.bin --expert-cache 64 --prefill auto --spec 3 --spec-min-p 0.5 --mtp rt --max-context 131072 --mmap-experts --adapt-every 100000Strata, IQ3_XXS, no MTP
--pack iq3_xxs --native Qwen3.8-Flash-Next-GSQ-RCO-IQ3_XXS-00001-of-00002.gguf --ple-gguf Qwen3.8-Flash-Next-GSQ-RCO-IQ3_XXS-00002-of-00002.gguf --expert-profile expert-profile.bin --expert-cache 64 --prefill auto --spec 2 --suffix-draft 0 --max-context 131072 --mmap-experts --adapt-every 100000Strata, IQ3_S, no MTP
--pack iq3_s --native Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-00001-of-00002.gguf --ple-gguf Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-00002-of-00002.gguf --expert-profile expert-profile.bin --expert-cache 64 --prefill auto --spec 2 --suffix-draft 0 --max-context 131072 --mmap-experts --adapt-every 100000Qwen-Image-2.1 Base: Text to image, Image edit
Qwen-Image-2.1 Turbo: Image edit
--listen 127.0.0.1 --port 8288 --extra-model-paths-config extra_model_paths.yaml --output-directory images --input-directory inputs --gpu-onlyQwen-Image-2.1 Base: Text to image, Image edit
Qwen-Image-2.1 Turbo: Image edit
--listen 127.0.0.1 --port 8288 --extra-model-paths-config extra_model_paths.yaml --output-directory images --input-directory inputsComfyUI, nvfp4
--listen 127.0.0.1 --port 8288 --disable-auto-launch --extra-model-paths-config extra_model_paths.yaml --output-directory outputs --gpu-only