Back to leaderboard

qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx

LM-STUDIO MLX

qwen3_moe · 30B · MXFP4

Excellent

Apr 22, 2026 · Apple M2 Max

qwen3-coder:30b

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

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

Global Score
95 vs 80
Hardware Fit
94 vs 60
Quality Score
96 vs 88

Hardware

qwen3-30b-a3b-thin… qwen3-coder:30b
MachineMac StudioASUS
CPUApple M2 MaxIntel Gen Intel® Core™ i7-12700K
Cores1220
RAM96 GB96 GB
GPUApple M2 MaxParsec Virtual Display Adapter, NVIDIA GeForce RTX 2060
OSmacOS 26.1Microsoft Windows 11 Enterprise 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3-30b-a3b-thin… qwen3-coder:30b
Tokens/sec80.414.7
First chunk46 ms796 ms
TTFT1.8 s796 ms
Load timeN/A0.2 s
Memory usage21.2 GB17.9 GB
Memory %22%19%

HW Fit Score Breakdown

qwen3-30b-a3b-thinking-…

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

qwen3-coder:30b

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

Quality

qwen3-30b-a3b-thinking-…

Reasoning
19/20
Coding
18/20
Instruction
19/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

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
View qwen3-30b-a3b-thin… details | View qwen3-coder:30b 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