Back to leaderboard

qwen2.5-coder:7b

OLLAMA GGUF

qwen2 · 7.6B · Q4_K_M

Good

Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K

qwen3.8-27b-mlx

LM-STUDIO UNKNOWN

27B

Good

Aug 17, 2026 · Apple M5 Max

Global Score
68 vs 66
Hardware Fit
59 vs 91
Quality Score
72 vs 55

Hardware

qwen2.5-coder:7b qwen3.8-27b-mlx
MachineASUSMacBook Pro
CPUIntel Gen Intel® Core™ i7-13700KApple M5 Max
Cores2418
RAM64 GB64 GB
GPUNVIDIA GeForce RTX 3070Apple M5 Max
OSMicrosoft Windows 11 Pro 10.0.26200macOS 27.0
Archx64arm64
Power Modeunknownbalanced

Performance

qwen2.5-coder:7b qwen3.8-27b-mlx
Tokens/sec34.433.2
First chunk1991 ms7 ms
TTFT2.0 s311 ms
Load time40.6 sN/A
Memory usage5.0 GB0.5 GB
Memory %8%1%

HW Fit Score Breakdown

qwen2.5-coder:7b

Speed
38/50
TTFT
12/20
Memory
9/30

qwen3.8-27b-mlx

Speed
41/50
TTFT
20/20
Memory
30/30

Quality

qwen2.5-coder:7b

Reasoning
11/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
9/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

qwen3.8-27b-mlx

Reasoning
19/20
Coding
13/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
3/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak

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