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 20, 2026 · Apple M2 Max

gemma4:26b

OLLAMA GGUF

gemma4 · 25.8B · Q4_K_M

Not Rec.

Apr 3, 2026 · Apple M4

Global Score
97 vs 33
Hardware Fit
95 vs 50
Quality Score
98 vs 25

Hardware

qwen3-30b-a3b-thin… gemma4:26b
MachineMac StudioMac mini
CPUApple M2 MaxApple M4
Cores1210
RAM96 GB24 GB
GPUApple M2 MaxApple M4
OSmacOS 26.1macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3-30b-a3b-thin… gemma4:26b
Tokens/sec79.620.0
First chunk11 ms941 ms
TTFT1.7 s30.0 s
Load time7.1 s0.2 s
Memory usage0.0 GB20.3 GB
Memory %0%85%

HW Fit Score Breakdown

qwen3-30b-a3b-thinking-…

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

gemma4:26b

Speed
42/50
TTFT
0/20
Memory
8/30

Quality

qwen3-30b-a3b-thinking-…

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

gemma4:26b

Reasoning
14/20
Coding
1/20
Instruction
6/20
Structured
3/15
Math
0/15
Multilingual
1/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor
View qwen3-30b-a3b-thin… details | View gemma4:26b 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