Back to leaderboard

Qwen3-30B:30b

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

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

qwen3.8-27b-mlx

LM-STUDIO UNKNOWN

27B

Good

Aug 17, 2026 · Apple M5 Max

Global Score
88 vs 66
Hardware Fit
91 vs 91
Quality Score
87 vs 55

Hardware

Qwen3-30B:30b qwen3.8-27b-mlx
MachineHP HyperX OMEN Gaming Laptop 16-ap1xxxMacBook Pro
CPUAMD Ryzen 9 9955HX3D 16-Core ProcessorApple M5 Max
Cores3218
RAM31 GB64 GB
GPUAMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPUApple M5 Max
OSMicrosoft Windows 11 Home 10.0.26200macOS 27.0
Archx64arm64
Power Modebalancedbalanced

Performance

Qwen3-30B:30b qwen3.8-27b-mlx
Tokens/sec42.533.2
First chunk442 ms7 ms
TTFT442 ms311 ms
Load time21.7 sN/A
Memory usage17.9 GB0.5 GB
Memory %58%1%

HW Fit Score Breakdown

Qwen3-30B:30b

Speed
50/50
TTFT
20/20
Memory
21/30

qwen3.8-27b-mlx

Speed
41/50
TTFT
20/20
Memory
30/30

Quality

Qwen3-30B:30b

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.8-27b-mlx

Reasoning
19/20
Coding
13/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
3/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak

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