Back to leaderboard

gemma4:31b

OLLAMA GGUF

gemma4 · 30.7B · Q4_K_M

Not Rec.

Oct 2, 2026 · AMD Ryzen 9 5950X 16-Core Processor

llama3.2:3b

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Nov 4, 2026 · Intel Core™ i7-9700

Global Score
64 vs 71
Hardware Fit
41 vs 90
Quality Score
74 vs 63

Hardware

gemma4:31b llama3.2:3b
MachineSystem manufacturerVMware, Inc. VMware Virtual Platform
CPUAMD Ryzen 9 5950X 16-Core ProcessorIntel Core™ i7-9700
Cores324
RAM32 GB16 GB
GPUNVIDIA GeForce RTX 3090Integrated / Unknown
OSMicrosoft Windows 11 Pro 10.0.26300Ubuntu 24.04.5 LTS
Archx64x64
Power Modebalancedunknown

Performance

gemma4:31b llama3.2:3b
Tokens/sec9.513.0
First chunk1751 ms536 ms
TTFT30.0 s536 ms
Load time33.9 s82.5 s
Memory usage1.4 GB2.4 GB
Memory %4%15%

HW Fit Score Breakdown

gemma4:31b

Speed
11/50
TTFT
0/20
Memory
30/30

llama3.2:3b

Speed
40/50
TTFT
20/20
Memory
30/30

Quality

gemma4:31b

Reasoning
11/20
Coding
17/20
Instruction
10/20
Structured
15/15
Math
12/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

llama3.2:3b

Reasoning
11/20
Coding
14/20
Instruction
14/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor 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