Back to leaderboard

mlx-community/quantized-gemma-2b-it

LM-STUDIO GGUF
Marginal

Mar 5, 2026 · Apple M4

qwen3:30b-a3b-instruct-2507-q4_K_M

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Not Rec.

Jul 31, 2026 · Intel Xeon® E5-4620 0

Global Score
45 vs 71
Hardware Fit
100 vs 42
Quality Score
21 vs 84

Hardware

mlx-community/quan… qwen3:30b-a3b-inst…
MachineMacBook AirDell Inc. PowerEdge R820
CPUApple M4Intel Xeon® E5-4620 0
Cores1064
RAM32 GB256 GB
GPUApple M4Microsoft Remote Display Adapter, Microsoft Basic Display Adapter
OSmacOS 26.3Microsoft Windows Server 2022 Datacenter 10.0.20348
Archarm64x64
Power Modebalancedbalanced

Performance

mlx-community/quan… qwen3:30b-a3b-inst…
Tokens/sec44.44.0
First chunk336 ms2070 ms
TTFT336 ms2.1 s
Load timeN/A44.5 s
Memory usage0.1 GB17.7 GB
Memory %0%7%

HW Fit Score Breakdown

mlx-community/quantized…

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

qwen3:30b-a3b-instruct-…

Speed
3/50
TTFT
9/20
Memory
30/30

Quality

mlx-community/quantized…

Reasoning
4/20
Coding
1/20
Instruction
9/20
Structured
4/15
Math
2/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Poor Multilingual: Poor

qwen3:30b-a3b-instruct-…

Reasoning
18/20
Coding
18/20
Instruction
11/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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