Back to leaderboard

qwen3-coder-30b-a3b-instruct-mlx

LM-STUDIO MLX

qwen3_moe · 30B · 4bit

Excellent

Oct 20, 2026 · Apple M1 Pro

qwen2.5-coder:7b

OLLAMA GGUF

qwen2 · 7.6B · Q4_K_M

Good

Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K

Global Score
87 vs 68
Hardware Fit
85 vs 59
Quality Score
88 vs 72

Hardware

qwen3-coder-30b-a3… qwen2.5-coder:7b
MachineMacBook ProASUS
CPUApple M1 ProIntel Gen Intel® Core™ i7-13700K
Cores1024
RAM32 GB64 GB
GPUApple M1 ProNVIDIA GeForce RTX 3070
OSmacOS 15.6.1Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedunknown

Performance

qwen3-coder-30b-a3… qwen2.5-coder:7b
Tokens/sec45.734.4
First chunk17 ms1991 ms
TTFT390 ms2.0 s
Load timeN/A40.6 s
Memory usage22.4 GB5.0 GB
Memory %70%8%

HW Fit Score Breakdown

qwen3-coder-30b-a3b-ins…

Speed
50/50
TTFT
20/20
Memory
15/30

qwen2.5-coder:7b

Speed
38/50
TTFT
12/20
Memory
9/30

Quality

qwen3-coder-30b-a3b-ins…

Reasoning
15/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen2.5-coder:7b

Reasoning
11/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
9/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3-coder-30b-a3… details | View qwen2.5-coder:7b 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