Back to leaderboard

qwen3-coder:30b

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Jun 18, 2026 · AMD Ryzen 5 5500U

qwen3.5-0.8b-mlx

LM-STUDIO MLX

qwen3_5 · 0.8B · 4bit

Marginal

Mar 6, 2026 · Apple M4 Pro

Global Score
82 vs 53
Hardware Fit
71 vs 89
Quality Score
87 vs 38

Hardware

qwen3-coder:30b qwen3.5-0.8b-mlx
MachineHP HP Pavilion Laptop 15-eh1xxxMac mini
CPUAMD Ryzen 5 5500UApple M4 Pro
Cores1214
RAM63 GB64 GB
GPUAMD Radeon(TM) GraphicsApple M4 Pro
OSMicrosoft Windows 10 Enterprise LTSC 10.0.19044macOS 15.7.4
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3-coder:30b qwen3.5-0.8b-mlx
Tokens/sec14.352.9
First chunk869 ms4013 ms
TTFT869 ms4.0 s
Load time0.3 sN/A
Memory usage20.5 GB0.6 GB
Memory %32%1%

HW Fit Score Breakdown

qwen3-coder:30b

Speed
22/50
TTFT
20/20
Memory
29/30

qwen3.5-0.8b-mlx

Speed
50/50
TTFT
9/20
Memory
30/30

Quality

qwen3-coder:30b

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.5-0.8b-mlx

Reasoning
7/20
Coding
2/20
Instruction
12/20
Structured
10/15
Math
2/15
Multilingual
5/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Adequate
View qwen3-coder:30b details | View qwen3.5-0.8b-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