Back to leaderboard

qwen3.5-4b-mlx

LM-STUDIO MLX

qwen3_5 · 4B · 4bit

Not Rec.

Mar 6, 2026 · Apple M4 Pro

llama3.2:3b

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Mar 2, 2026 · Apple M4

Global Score
62 vs 74
Hardware Fit
35 vs 100
Quality Score
73 vs 63

Hardware

qwen3.5-4b-mlx llama3.2:3b
MachineMac miniMacBook Air
CPUApple M4 ProApple M4
Cores1410
RAM64 GB32 GB
GPUApple M4 ProApple M4
OSmacOS 15.7.4macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5-4b-mlx llama3.2:3b
Tokens/sec0.044.1
First chunk5548 msN/A
TTFT5.5 s178 ms
Load timeN/A0.8 s
Memory usage2.9 GB7.0 GB
Memory %5%22%

HW Fit Score Breakdown

qwen3.5-4b-mlx

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

llama3.2:3b

Speed
40/50
TTFT
30/20
Memory
30/30

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

llama3.2:3b

Reasoning
11/20
Coding
14/20
Instruction
14/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
View qwen3.5-4b-mlx details | View llama3.2:3b 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