qwen3.6:35b
OLLAMA GGUFqwen35moe · 36.0B · Q4_K_M
May 25, 2026 · Apple M4 Pro
qwen2.5:72b
OLLAMA GGUFqwen2 · 72.7B · Q4_K_M
Jun 27, 2026 · Cortex-X925
Global Score
70 vs 75
Hardware Fit
66 vs 50
Quality Score
71 vs 86
Hardware
qwen3.6:35b qwen2.5:72b
MachineMacBook ProNVIDIA NVIDIA_DGX_Spark
CPUApple M4 ProCortex-X925
Cores1420
RAM48 GB122 GB
GPUApple M4 ProDevice 2e12
OSmacOS 26.4.1Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance
Performance
qwen3.6:35b qwen2.5:72b
Tokens/sec30.64.4
First chunk304 ms529 ms
TTFT30.0 s529 ms
Load time10.0 s49.7 s
Memory usage28.1 GB54.0 GB
Memory %59%44%
HW Fit Score Breakdown
qwen3.6:35b
Speed
45/50
TTFT
0/20
Memory
21/30
qwen2.5:72b
Speed
4/50
TTFT
20/20
Memory
26/30
Quality
qwen3.6:35b
Reasoning
18/20
Coding
12/20
Instruction
12/20
Structured
6/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Adequate Structured Output: Weak Math: Strong Multilingual: Strong
qwen2.5:72b
Reasoning
19/20
Coding
19/20
Instruction
12/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest