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

Gemma4-26B:26b

OLLAMA GGUF

gemma4 · 25.8B · Q4_K_M

Excellent

Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor

Global Score
96 vs 91
Hardware Fit
95 vs 93
Quality Score
96 vs 90

Hardware

qwen3-30b-a3b-thin… Gemma4-26B:26b
MachineMacBook ProHP HyperX OMEN Gaming Laptop 16-ap1xxx
CPUApple M4 MaxAMD Ryzen 9 9955HX3D 16-Core Processor
Cores1632
RAM128 GB31 GB
GPUApple M4 MaxAMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPU
OSmacOS 26.5.2Microsoft Windows 11 Home 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3-30b-a3b-thin… Gemma4-26B:26b
Tokens/sec112.840.5
First chunk21 ms727 ms
TTFT1.5 s727 ms
Load time3.5 s25.3 s
Memory usage0.0 GB17.0 GB
Memory %0%55%

HW Fit Score Breakdown

qwen3-30b-a3b-thinking-…

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

Gemma4-26B:26b

Speed
50/50
TTFT
20/20
Memory
23/30

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

Gemma4-26B:26b

Reasoning
17/20
Coding
19/20
Instruction
17/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

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