Back to leaderboard

qwen3.5-4b-mlx

LM-STUDIO MLX

qwen3_5 · 4B · 4bit

Not Rec.

Mar 6, 2026 · Apple M4 Pro

llama4:scout

OLLAMA GGUF

llama4 · 108.6B · Q4_K_M

Excellent

Oct 3, 2026 · Cortex-X925

Global Score
62 vs 81
Hardware Fit
35 vs 64
Quality Score
73 vs 88

Hardware

qwen3.5-4b-mlx llama4:scout
MachineMac miniNVIDIA NVIDIA_DGX_Spark
CPUApple M4 ProCortex-X925
Cores1420
RAM64 GB122 GB
GPUApple M4 ProDevice 2e12
OSmacOS 15.7.4Ubuntu 24.04.5 LTS
Archarm64arm64
Power Modebalancedperformance

Performance

qwen3.5-4b-mlx llama4:scout
Tokens/sec0.019.6
First chunk5548 ms677 ms
TTFT5.5 s677 ms
Load timeN/A13.1 s
Memory usage2.9 GB63.4 GB
Memory %5%52%

HW Fit Score Breakdown

qwen3.5-4b-mlx

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

llama4:scout

Speed
20/50
TTFT
20/20
Memory
24/30

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

llama4:scout

Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
13/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.5-4b-mlx details | View llama4:scout 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