Back to leaderboard

qwen/qwen3.8-27b

LM-STUDIO MLX

qwen3_5 · 27B · 4bit

Excellent

Aug 18, 2026 · Apple M4 Max

qwen2.5:14b

OLLAMA GGUF

qwen2 · 14.8B · Q4_K_M

Excellent

Sep 15, 2026 · Intel Core™ i5-14400F

Global Score
87 vs 90
Hardware Fit
83 vs 100
Quality Score
88 vs 85

Hardware

qwen/qwen3.8-27b qwen2.5:14b
MachineMacBook ProGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUApple M4 MaxIntel Core™ i5-14400F
Cores1616
RAM128 GB32 GB
GPUApple M4 MaxNVIDIA GeForce RTX 5060 Ti
OSmacOS 26.5.2Microsoft Windows 11 Professionnel 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen/qwen3.8-27b qwen2.5:14b
Tokens/sec29.137.8
First chunk9 ms74 ms
TTFT650 ms74 ms
Load timeN/A6.2 s
Memory usage21.0 GB8.8 GB
Memory %16%28%

HW Fit Score Breakdown

qwen/qwen3.8-27b

Speed
33/50
TTFT
20/20
Memory
30/30

qwen2.5:14b

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

Quality

qwen/qwen3.8-27b

Reasoning
18/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

qwen2.5:14b

Reasoning
17/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen/qwen3.8-27b details | View qwen2.5:14b 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