Back to leaderboard

qwen3-4b-qwen3.6-plus-reasoning-distilled

LM-STUDIO GGUF

qwen3 · 4B · Q4_1

Good

Apr 21, 2026 · Apple M2 Max

lfm2.5-1.2b-instruct-mlx

LM-STUDIO MLX

lfm2 · 1.2B · 8bit

Good

Mar 4, 2026 · Apple M4

Global Score
65 vs 68
Hardware Fit
96 vs 100
Quality Score
51 vs 54

Hardware

qwen3-4b-qwen3.6-p… lfm2.5-1.2b-instru…
MachineMac StudioMacBook Air
CPUApple M2 MaxApple M4
Cores1210
RAM96 GB32 GB
GPUApple M2 MaxApple M4
OSmacOS 26.1macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3-4b-qwen3.6-p… lfm2.5-1.2b-instru…
Tokens/sec99.677.3
First chunk18 ms177 ms
TTFT1.6 s177 ms
Load time4.8 sN/A
Memory usage0.3 GB1.2 GB
Memory %0%4%

HW Fit Score Breakdown

qwen3-4b-qwen3.6-plus-r…

Speed
50/50
TTFT
16/20
Memory
30/30

lfm2.5-1.2b-instruct-mlx

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

Quality

qwen3-4b-qwen3.6-plus-r…

Reasoning
8/20
Coding
4/20
Instruction
14/20
Structured
9/15
Math
8/15
Multilingual
8/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Adequate Multilingual: Strong

lfm2.5-1.2b-instruct-mlx

Reasoning
10/20
Coding
7/20
Instruction
16/20
Structured
12/15
Math
1/15
Multilingual
8/10
Reasoning: Weak Coding: Weak Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong
View qwen3-4b-qwen3.6-p… details | View lfm2.5-1.2b-instru… 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