Back to leaderboard

qwen3.8-27b-mlx

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Marginal

Aug 17, 2026 · Apple M5 Max

lfm2.5:8b

OLLAMA GGUF

lfm2moe · 8.5B · Q4_K_M

Excellent

Aug 24, 2026 · Apple M1 Pro

Global Score
59 vs 80
Hardware Fit
63 vs 95
Quality Score
58 vs 73

Hardware

qwen3.8-27b-mlx lfm2.5:8b
MachineMacBook ProMacBook Pro
CPUApple M5 MaxApple M1 Pro
Cores1810
RAM64 GB16 GB
GPUApple M5 MaxApple M1 Pro
OSmacOS 27.0macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.8-27b-mlx lfm2.5:8b
Tokens/sec18.398.5
First chunk4 ms167 ms
TTFT530 ms2.5 s
Load timeN/A3.0 s
Memory usage38.5 GB6.0 GB
Memory %60%37%

HW Fit Score Breakdown

qwen3.8-27b-mlx

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

lfm2.5:8b

Speed
50/50
TTFT
17/20
Memory
28/30

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

lfm2.5:8b

Reasoning
2/20
Coding
12/20
Instruction
19/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Poor Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong 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