Back to leaderboard

qwen3-coder:30b

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Mar 4, 2026 · Intel Gen Intel® Core™ i7-12700K

qwen3.5-4b-mlx

LM-STUDIO MLX

qwen3_5 · 4B · 4bit

Not Rec.

Mar 6, 2026 · Apple M4 Pro

Global Score
80 vs 62
Hardware Fit
60 vs 35
Quality Score
88 vs 73

Hardware

qwen3-coder:30b qwen3.5-4b-mlx
MachineASUSMac mini
CPUIntel Gen Intel® Core™ i7-12700KApple M4 Pro
Cores2014
RAM96 GB64 GB
GPUParsec Virtual Display Adapter, NVIDIA GeForce RTX 2060Apple M4 Pro
OSMicrosoft Windows 11 Enterprise 10.0.26200macOS 15.7.4
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3-coder:30b qwen3.5-4b-mlx
Tokens/sec14.70.0
First chunk796 ms5548 ms
TTFT796 ms5.5 s
Load time0.2 sN/A
Memory usage17.9 GB2.9 GB
Memory %19%5%

HW Fit Score Breakdown

qwen3-coder:30b

Speed
14/50
TTFT
19/20
Memory
27/30

qwen3.5-4b-mlx

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

Quality

qwen3-coder:30b

Reasoning
17/20
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: Adequate Multilingual: Strong

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
View qwen3-coder:30b details | View qwen3.5-4b-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