Back to leaderboard

qwen3.8-27b-mlx

LM-STUDIO UNKNOWN

27B

Good

Aug 17, 2026 · Apple M5 Max

qwen2.5-coder:7b

OLLAMA GGUF

qwen2 · 7.6B · Q4_K_M

Good

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

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

Hardware

qwen3.8-27b-mlx qwen2.5-coder:7b
MachineMacBook ProASUS
CPUApple M5 MaxIntel Gen Intel® Core™ i7-13700K
Cores1824
RAM64 GB64 GB
GPUApple M5 MaxNVIDIA GeForce RTX 3070
OSmacOS 27.0Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedunknown

Performance

qwen3.8-27b-mlx qwen2.5-coder:7b
Tokens/sec33.234.4
First chunk7 ms1991 ms
TTFT311 ms2.0 s
Load timeN/A40.6 s
Memory usage0.5 GB5.0 GB
Memory %1%8%

HW Fit Score Breakdown

qwen3.8-27b-mlx

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

qwen2.5-coder:7b

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

Quality

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

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

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