Back to leaderboard

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Good

Aug 25, 2026 · Apple M1 Pro

lfm2:24b

OLLAMA GGUF

lfm2moe · 23.8B · Q4_K_M

Excellent

Mar 27, 2026 · AMD RYZEN AI MAX+ 395

Global Score
68 vs 88
Hardware Fit
91 vs 100
Quality Score
58 vs 83

Hardware

qwen3.5:4b-mlx lfm2:24b
MachineMacBook ProAZW GTR Pro
CPUApple M1 ProAMD RYZEN AI MAX+ 395
Cores1032
RAM16 GB125 GB
GPUApple M1 ProRadeon 8060S
OSmacOS 26.6.2Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedperformance

Performance

qwen3.5:4b-mlx lfm2:24b
Tokens/sec42.295.4
First chunk201 ms202 ms
TTFT4.4 s202 ms
Load time0.0 s5.0 s
Memory usage3.8 GB14.3 GB
Memory %24%12%

HW Fit Score Breakdown

qwen3.5:4b-mlx

Speed
50/50
TTFT
11/20
Memory
30/30

lfm2:24b

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

Quality

qwen3.5:4b-mlx

Reasoning
16/20
Coding
2/20
Instruction
13/20
Structured
7/15
Math
11/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Weak Math: Adequate Multilingual: Strong

lfm2:24b

Reasoning
14/20
Coding
17/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.5:4b-mlx details | View lfm2:24b 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