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:e2b

OLLAMA GGUF

gemma4 · 5.1B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

Global Score
97 vs 76
Hardware Fit
95 vs 82
Quality Score
98 vs 73

Hardware

qwen3-30b-a3b-thin… gemma4:e2b
MachineMac StudioLENOVO 20U30029MB
CPUApple M2 MaxIntel Core™ i5-10210U
Cores128
RAM96 GB15 GB
GPUApple M2 MaxCometLake-U GT2 [UHD Graphics]
OSmacOS 26.1Pop 24.04 LTS
Archarm64x64
Power Modebalancedperformance

Performance

qwen3-30b-a3b-thin… gemma4:e2b
Tokens/sec79.613.5
First chunk11 ms1270 ms
TTFT1.7 s1.3 s
Load time7.1 s13.4 s
Memory usage0.0 GB6.5 GB
Memory %0%42%

HW Fit Score Breakdown

qwen3-30b-a3b-thinking-…

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

gemma4:e2b

Speed
35/50
TTFT
20/20
Memory
27/30

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:e2b

Reasoning
10/20
Coding
15/20
Instruction
16/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3-30b-a3b-thin… details | View gemma4:e2b 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