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

qwen36-distill-apex

OLLAMA GGUF
Not Rec.

Jul 17, 2026 · Apple M5 Max

Global Score
95 vs 36
Hardware Fit
94 vs 100
Quality Score
96 vs 8

Hardware

qwen3-30b-a3b-thin… qwen36-distill-apex
MachineMac StudioMacBook Pro
CPUApple M2 MaxApple M5 Max
Cores1218
RAM96 GB64 GB
GPUApple M2 MaxApple M5 Max
OSmacOS 26.1macOS 27.0
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3-30b-a3b-thin… qwen36-distill-apex
Tokens/sec80.455.2
First chunk46 ms210 ms
TTFT1.8 s210 ms
Load timeN/A4.8 s
Memory usage21.2 GB0.9 GB
Memory %22%2%

HW Fit Score Breakdown

qwen3-30b-a3b-thinking-…

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

qwen36-distill-apex

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

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

qwen36-distill-apex

Reasoning
8/20
Coding
0/20
Instruction
0/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
View qwen3-30b-a3b-thin… details | View qwen36-distill-apex 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