Back to leaderboard

qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx

LM-STUDIO MLX

qwen3_moe · 30B · MXFP4

Excellent

Aug 20, 2026 · Apple M4 Max

gemma4:e2b

OLLAMA GGUF

gemma4 · 4.6B · Q4_K_M

Excellent

Oct 12, 2026 · AMD Ryzen 5 5500

Global Score
96 vs 93
Hardware Fit
95 vs 100
Quality Score
96 vs 90

Hardware

qwen3-30b-a3b-thin… gemma4:e2b
MachineMacBook ProMicrosoft WSL
CPUApple M4 MaxAMD Ryzen 5 5500
Cores1612
RAM128 GB8 GB
GPUApple M4 MaxIntegrated / Unknown
OSmacOS 26.5.2Ubuntu 26.04.1 LTS
Archarm64x64
Power Modebalancedunknown

Performance

qwen3-30b-a3b-thin… gemma4:e2b
Tokens/sec112.8141.2
First chunk21 ms94 ms
TTFT1.5 s1.6 s
Load time3.5 s18.4 s
Memory usage0.0 GB0.2 GB
Memory %0%3%

HW Fit Score Breakdown

qwen3-30b-a3b-thinking-…

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

gemma4:e2b

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

gemma4:e2b

Reasoning
18/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
15/15
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: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