Back to leaderboard

qwen3:8b

OLLAMA GGUF

qwen3 · 8.2B · Q4_K_M

Good

Aug 15, 2026 · AMD Ryzen 9 3900X 12-Core Processor

qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 4bit

Good

Mar 6, 2026 · Apple M4 Pro

Global Score
78 vs 65
Hardware Fit
86 vs 88
Quality Score
74 vs 55

Hardware

qwen3:8b qwen3.5-2b-mlx
Machine—Mac mini
CPUAMD Ryzen 9 3900X 12-Core ProcessorApple M4 Pro
Cores2414
RAM64 GB64 GB
GPUNVIDIA GeForce RTX 4060 TiApple M4 Pro
OSMicrosoft Windows 11 Pro 10.0.26200macOS 15.7.4
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3:8b qwen3.5-2b-mlx
Tokens/sec48.548.9
First chunk202 ms4208 ms
TTFT4.3 s4.2 s
Load time4.2 sN/A
Memory usage5.5 GB1.6 GB
Memory %9%3%

HW Fit Score Breakdown

qwen3:8b

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

qwen3.5-2b-mlx

Speed
50/50
TTFT
8/20
Memory
30/30

Quality

qwen3:8b

Reasoning
16/20
Coding
8/20
Instruction
14/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.5-2b-mlx

Reasoning
10/20
Coding
7/20
Instruction
13/20
Structured
14/15
Math
3/15
Multilingual
8/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
View qwen3:8b details | View qwen3.5-2b-mlx 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