Back to leaderboard

qwen3.8-27b-mlx

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Marginal

Aug 17, 2026 · Apple M5 Max

qwen2.5:1.5b

OLLAMA GGUF

qwen2 · 1.5B · Q4_K_M

Good

Jun 17, 2026 · ZHAOXIN KaiXian KX-7000 KaiXian KX-7000

Global Score
59 vs 65
Hardware Fit
63 vs 87
Quality Score
58 vs 56

Hardware

qwen3.8-27b-mlx qwen2.5:1.5b
MachineMacBook ProShanghai Zhaoxin Semiconductor Co., Ltd. ZXE CRB
CPUApple M5 MaxZHAOXIN KaiXian KX-7000 KaiXian KX-7000
Cores188
RAM64 GB30 GB
GPUApple M5 MaxZX C-1190
OSmacOS 27.0Microsoft Windows 11 Pro 10.0.26100
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.8-27b-mlx qwen2.5:1.5b
Tokens/sec18.316.8
First chunk4 ms941 ms
TTFT530 ms941 ms
Load timeN/A0.2 s
Memory usage38.5 GB1.0 GB
Memory %60%3%

HW Fit Score Breakdown

qwen3.8-27b-mlx

Speed
23/50
TTFT
20/20
Memory
20/30

qwen2.5:1.5b

Speed
37/50
TTFT
20/20
Memory
30/30

Quality

qwen3.8-27b-mlx

Reasoning
19/20
Coding
14/20
Instruction
6/20
Structured
1/15
Math
13/15
Multilingual
5/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak

qwen2.5:1.5b

Reasoning
8/20
Coding
10/20
Instruction
12/20
Structured
13/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3.8-27b-mlx details | View qwen2.5:1.5b 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