Back to leaderboard

qwen2.5:7b

OLLAMA GGUF

qwen2 · 7.6B · Q4_K_M

Excellent

Nov 3, 2026 · Intel Gen Intel® Core™ i9-12900HX

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Good

Aug 25, 2026 · Apple M1 Pro

Global Score
85 vs 68
Hardware Fit
100 vs 91
Quality Score
79 vs 58

Hardware

qwen2.5:7b qwen3.5:4b-mlx
MachineMACHENIKE L16PMacBook Pro
CPUIntel Gen Intel® Core™ i9-12900HXApple M1 Pro
Cores2410
RAM32 GB16 GB
GPUNVIDIA GeForce RTX 4060 Laptop GPUApple M1 Pro
OSMicrosoft Windows 11 专业版 10.0.26300macOS 26.6.2
Archx64arm64
Power Modebalancedbalanced

Performance

qwen2.5:7b qwen3.5:4b-mlx
Tokens/sec52.342.2
First chunk50 ms201 ms
TTFT50 ms4.4 s
Load time2.0 s0.0 s
Memory usage4.4 GB3.8 GB
Memory %14%24%

HW Fit Score Breakdown

qwen2.5:7b

Speed
50/50
TTFT
20/20
Memory
30/30

qwen3.5:4b-mlx

Speed
50/50
TTFT
11/20
Memory
30/30

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

qwen3.5:4b-mlx

Reasoning
16/20
Coding
2/20
Instruction
13/20
Structured
7/15
Math
11/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Weak Math: Adequate Multilingual: Strong
View qwen2.5:7b details | View qwen3.5:4b-mlx details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest