qwen2.5:7b
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Nov 3, 2026 · Intel Gen Intel® Core™ i9-12900HX
qwen3.6:35b
OLLAMA GGUFqwen35moe · 36.0B · Q4_K_M
May 25, 2026 · Apple M4 Pro
Global Score
85 vs 70
Hardware Fit
100 vs 66
Quality Score
79 vs 71
Hardware
qwen2.5:7b qwen3.6:35b
MachineMACHENIKE L16PMacBook Pro
CPUIntel Gen Intel® Core™ i9-12900HXApple M4 Pro
Cores2414
RAM32 GB48 GB
GPUNVIDIA GeForce RTX 4060 Laptop GPUApple M4 Pro
OSMicrosoft Windows 11 专业版 10.0.26300macOS 26.4.1
Archx64arm64
Power Modebalancedbalanced
Performance
qwen2.5:7b qwen3.6:35b
Tokens/sec52.430.6
First chunk48 ms304 ms
TTFT48 ms30.0 s
Load time2.0 s10.0 s
Memory usage4.4 GB28.1 GB
Memory %14%59%
HW Fit Score Breakdown
qwen2.5:7b
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3.6:35b
Speed
45/50
TTFT
0/20
Memory
21/30
Quality
qwen2.5:7b
Reasoning
14/20
Coding
18/20
Instruction
16/20
Structured
14/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
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
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