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

cogito:3b

OLLAMA GGUF

llama · 3.6B · Q4_K_M

Good

Mar 6, 2026 · Apple M4

Global Score
95 vs 67
Hardware Fit
94 vs 100
Quality Score
96 vs 53

Hardware

qwen3-30b-a3b-thin… cogito:3b
MachineMac StudioMacBook Air
CPUApple M2 MaxApple M4
Cores1210
RAM96 GB32 GB
GPUApple M2 MaxApple M4
OSmacOS 26.1macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3-30b-a3b-thin… cogito:3b
Tokens/sec80.445.6
First chunk46 ms177 ms
TTFT1.8 s177 ms
Load timeN/A0.8 s
Memory usage21.2 GB7.0 GB
Memory %22%22%

HW Fit Score Breakdown

qwen3-30b-a3b-thinking-…

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

cogito:3b

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

cogito:3b

Reasoning
6/20
Coding
8/20
Instruction
13/20
Structured
15/15
Math
2/15
Multilingual
9/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
View qwen3-30b-a3b-thin… details | View cogito:3b 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