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

Gemma4-31B:31B

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Aug 18, 2026 · Intel Core™ Ultra X7 358H

Global Score
95 vs 76
Hardware Fit
94 vs 45
Quality Score
96 vs 89

Hardware

qwen3-30b-a3b-thin… Gemma4-31B:31B
MachineMac StudioGMKtec NucBox EVO-T2S
CPUApple M2 MaxIntel Core™ Ultra X7 358H
Cores1216
RAM96 GB64 GB
GPUApple M2 MaxIntel(R) Arc(TM) B390 GPU
OSmacOS 26.1Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3-30b-a3b-thin… Gemma4-31B:31B
Tokens/sec80.43.8
First chunk46 ms3536 ms
TTFT1.8 s3.5 s
Load timeN/A19.6 s
Memory usage21.2 GB19.9 GB
Memory %22%31%

HW Fit Score Breakdown

qwen3-30b-a3b-thinking-…

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

Gemma4-31B:31B

Speed
5/50
TTFT
10/20
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

Gemma4-31B:31B

Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
14/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3-30b-a3b-thin… details | View Gemma4-31B:31B 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