Back to leaderboard

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

gemma4:e4b

OLLAMA GGUF

gemma4 · 8.0B · Q4_K_M

Excellent

Apr 3, 2026 · AMD RYZEN AI MAX+ 395

Global Score
71 vs 84
Hardware Fit
42 vs 98
Quality Score
84 vs 78

Hardware

qwen3:30b-a3b-inst… gemma4:e4b
MachineDell Inc. PowerEdge R820AZW GTR Pro
CPUIntel Xeon® E5-4620 0AMD RYZEN AI MAX+ 395
Cores6432
RAM256 GB125 GB
GPUMicrosoft Remote Display Adapter, Microsoft Basic Display AdapterRadeon 8060S
OSMicrosoft Windows Server 2022 Datacenter 10.0.20348Ubuntu 24.04.4 LTS
Archx64x64
Power Modebalancedperformance

Performance

qwen3:30b-a3b-inst… gemma4:e4b
Tokens/sec4.053.0
First chunk2070 ms214 ms
TTFT2.1 s214 ms
Load time44.5 s3.1 s
Memory usage17.7 GB15.0 GB
Memory %7%12%

HW Fit Score Breakdown

qwen3:30b-a3b-instruct-…

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

gemma4:e4b

Speed
48/50
TTFT
20/20
Memory
30/30

Quality

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

gemma4:e4b

Reasoning
14/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak 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