Back to leaderboard

qwen/qwen3-30b-a3b-2507

LM-STUDIO GGUF

qwen3moe · 30B · Q3_K_L

Excellent

Jul 5, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

lfm2.5-thinking:1.2b

OLLAMA GGUF

lfm2 · 1.2B · Q4_K_M

Not Rec.

May 25, 2026 · Apple M4 Pro

Global Score
89 vs 60
Hardware Fit
90 vs 80
Quality Score
89 vs 52

Hardware

qwen/qwen3-30b-a3b… lfm2.5-thinking:1.2b
MachineASUSMacBook Pro
CPUAMD Ryzen 7 7800X3D 8-Core ProcessorApple M4 Pro
Cores1614
RAM31 GB48 GB
GPUNVIDIA GeForce RTX 4090, RaphaelApple M4 Pro
OScachyos rollingmacOS 26.4.1
Archx64arm64
Power Modeperformancebalanced

Performance

qwen/qwen3-30b-a3b… lfm2.5-thinking:1.2b
Tokens/sec151.8227.0
First chunk8 ms60 ms
TTFT74 ms30.0 s
Load timeN/A0.7 s
Memory usage18.5 GB2.6 GB
Memory %61%6%

HW Fit Score Breakdown

qwen/qwen3-30b-a3b-2507

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

lfm2.5-thinking:1.2b

Speed
50/50
TTFT
0/20
Memory
30/30

Quality

qwen/qwen3-30b-a3b-2507

Reasoning
18/20
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: Adequate Multilingual: Strong

lfm2.5-thinking:1.2b

Reasoning
8/20
Coding
6/20
Instruction
10/20
Structured
7/15
Math
12/15
Multilingual
9/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Weak Math: Strong Multilingual: Strong
View qwen/qwen3-30b-a3b… details | View lfm2.5-thinking:1.2b 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