Back to leaderboard

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Marginal

Mar 11, 2026 · Apple M4

lfm2.5-thinking:1.2b

OLLAMA GGUF

lfm2 · 1.2B · Q4_K_M

Not Rec.

May 25, 2026 · Apple M4 Pro

Global Score
58 vs 60
Hardware Fit
68 vs 80
Quality Score
54 vs 52

Hardware

qwen3.5-9b-mlx lfm2.5-thinking:1.2b
MachineMac miniMacBook Pro
CPUApple M4Apple M4 Pro
Cores1014
RAM24 GB48 GB
GPUApple M4Apple M4 Pro
OSmacOS 26.3macOS 26.4.1
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5-9b-mlx lfm2.5-thinking:1.2b
Tokens/sec16.7227.0
First chunk23 ms60 ms
TTFT14.1 s30.0 s
Load timeN/A0.7 s
Memory usage7.8 GB2.6 GB
Memory %33%6%

HW Fit Score Breakdown

qwen3.5-9b-mlx

Speed
36/50
TTFT
3/20
Memory
29/30

lfm2.5-thinking:1.2b

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

Quality

qwen3.5-9b-mlx

Reasoning
10/20
Coding
16/20
Instruction
4/20
Structured
9/15
Math
10/15
Multilingual
5/10
Reasoning: Adequate Coding: Strong Instruction Following: Poor Structured Output: Adequate Math: Adequate Multilingual: Adequate

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

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