Back to leaderboard

gemma4:e2b

OLLAMA GGUF

gemma4 · 5.1B · Q4_K_M

Good

May 24, 2026 · Intel Gen Intel® Core™ i7-1355U

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
72 vs 71
Hardware Fit
71 vs 42
Quality Score
72 vs 84

Hardware

gemma4:e2b qwen3:30b-a3b-inst…
MachineDell Inc. Inspiron 15 3530Dell Inc. PowerEdge R820
CPUIntel Gen Intel® Core™ i7-1355UIntel Xeon® E5-4620 0
Cores1264
RAM31 GB256 GB
GPURaptor Lake-P [Iris Xe Graphics]Microsoft Remote Display Adapter, Microsoft Basic Display Adapter
OScachyos rollingMicrosoft Windows Server 2022 Datacenter 10.0.20348
Archx64x64
Power Modelow-powerbalanced

Performance

gemma4:e2b qwen3:30b-a3b-inst…
Tokens/sec10.84.0
First chunk1408 ms2070 ms
TTFT1.4 s2.1 s
Load time6.0 s44.5 s
Memory usage7.2 GB17.7 GB
Memory %23%7%

HW Fit Score Breakdown

gemma4:e2b

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

qwen3:30b-a3b-instruct-…

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

Quality

gemma4:e2b

Reasoning
10/20
Coding
16/20
Instruction
14/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Weak Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

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