Back to leaderboard

qwen2.5:7b

OLLAMA GGUF

qwen2 · 7.6B · Q4_K_M

Excellent

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

qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 8bit

Good

Mar 3, 2026 · Apple M4

Global Score
85 vs 70
Hardware Fit
100 vs 93
Quality Score
79 vs 60

Hardware

qwen2.5:7b qwen3.5-2b-mlx
MachineMACHENIKE L16PMacBook Air
CPUIntel Gen Intel® Core™ i9-12900HXApple M4
Cores2410
RAM32 GB32 GB
GPUNVIDIA GeForce RTX 4060 Laptop GPUApple M4
OSMicrosoft Windows 11 专业版 10.0.26300macOS 26.3
Archx64arm64
Power Modebalancedbalanced

Performance

qwen2.5:7b qwen3.5-2b-mlx
Tokens/sec52.132.9
First chunk41 ms3096 ms
TTFT41 ms3.1 s
Load time2.1 sN/A
Memory usage4.4 GB2.5 GB
Memory %14%8%

HW Fit Score Breakdown

qwen2.5:7b

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

qwen3.5-2b-mlx

Speed
50/50
TTFT
13/20
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

qwen3.5-2b-mlx

Reasoning
11/20
Coding
9/20
Instruction
14/20
Structured
14/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
View qwen2.5:7b details | View qwen3.5-2b-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