Back to leaderboard

qwen3.5-4b-mlx

LM-STUDIO MLX

qwen3_5 · 4B · 4bit

Not Rec.

Mar 6, 2026 · Apple M4 Pro

GPT-120B:120b

OLLAMA GGUF

gptoss · 116.8B · MXFP4

Good

Aug 18, 2026 · Intel Core™ i7-14700F

Global Score
62 vs 79
Hardware Fit
35 vs 47
Quality Score
73 vs 93

Hardware

qwen3.5-4b-mlx GPT-120B:120b
MachineMac miniHP OMEN 35L VALORANT Limited Edition Gaming Desktop PC
CPUApple M4 ProIntel Core™ i7-14700F
Cores1428
RAM64 GB128 GB
GPUApple M4 ProNVIDIA GeForce RTX 5080
OSmacOS 15.7.4Microsoft Windows 11 Enterprise 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.5-4b-mlx GPT-120B:120b
Tokens/sec0.018.2
First chunk5548 ms1719 ms
TTFT5.5 s3.9 s
Load timeN/A50.9 s
Memory usage2.9 GB61.5 GB
Memory %5%48%

HW Fit Score Breakdown

qwen3.5-4b-mlx

Speed
0/50
TTFT
6/20
Memory
29/30

GPT-120B:120b

Speed
17/50
TTFT
5/20
Memory
25/30

Quality

qwen3.5-4b-mlx

Reasoning
17/20
Coding
17/20
Instruction
9/20
Structured
8/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Adequate Math: Strong Multilingual: Strong

GPT-120B:120b

Reasoning
19/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong 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