Back to leaderboard

qwen/qwen3-8b

LM-STUDIO MLX

qwen3 · 8B · 4bit

Excellent

Mar 5, 2026 · Apple M4 Pro

lfm2.5-thinking:1.2b

OLLAMA GGUF

lfm2 · 1.2B · Q4_K_M

Not Rec.

May 25, 2026 · Apple M4 Pro

Global Score
89 vs 60
Hardware Fit
95 vs 80
Quality Score
87 vs 52

Hardware

qwen/qwen3-8b lfm2.5-thinking:1.2b
MachineMac miniMacBook Pro
CPUApple M4 ProApple M4 Pro
Cores1414
RAM64 GB48 GB
GPUApple M4 ProApple M4 Pro
OSmacOS 15.7.4macOS 26.4.1
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen/qwen3-8b lfm2.5-thinking:1.2b
Tokens/sec33.4227.0
First chunk257 ms60 ms
TTFT257 ms30.0 s
Load timeN/A0.7 s
Memory usage4.3 GB2.6 GB
Memory %7%6%

HW Fit Score Breakdown

qwen/qwen3-8b

Speed
45/50
TTFT
20/20
Memory
30/30

lfm2.5-thinking:1.2b

Speed
50/50
TTFT
0/20
Memory
30/30

Quality

qwen/qwen3-8b

Reasoning
19/20
Coding
14/20
Instruction
16/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

lfm2.5-thinking:1.2b

Reasoning
8/20
Coding
6/20
Instruction
10/20
Structured
7/15
Math
12/15
Multilingual
9/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Weak Math: Strong Multilingual: Strong
View qwen/qwen3-8b details | View lfm2.5-thinking:1.2b 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