qwen3.5-4b-mlx
LM-STUDIO MLXqwen3_5 · 4B · 4bit
Mar 3, 2026 · Apple M4
rnj-1:8b
OLLAMA GGUFgemma3 · 8.3B · Q4_K_M
Aug 24, 2026 · Apple M1 Pro
Global Score
71 vs 80
Hardware Fit
88 vs 93
Quality Score
63 vs 74
Hardware
qwen3.5-4b-mlx rnj-1:8b
MachineMacBook AirMacBook Pro
CPUApple M4Apple M1 Pro
Cores1010
RAM32 GB16 GB
GPUApple M4Apple M1 Pro
OSmacOS 26.3macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5-4b-mlx rnj-1:8b
Tokens/sec23.122.3
First chunk3279 ms404 ms
TTFT3.3 s404 ms
Load timeN/A3.7 s
Memory usage2.9 GB8.3 GB
Memory %9%52%
HW Fit Score Breakdown
qwen3.5-4b-mlx
Speed
45/50
TTFT
13/20
Memory
30/30
rnj-1:8b
Speed
49/50
TTFT
20/20
Memory
24/30
Quality
qwen3.5-4b-mlx
Reasoning
15/20
Coding
16/20
Instruction
6/20
Structured
6/15
Math
11/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Weak Structured Output: Weak Math: Adequate Multilingual: Strong
rnj-1:8b
Reasoning
12/20
Coding
19/20
Instruction
15/20
Structured
5/15
Math
14/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Weak Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest