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

llama3.1:8b-instruct-q4_K_S

OLLAMA GGUF

llama · 8.0B · Q4_K_S

Good

Nov 22, 2026 · C1-Pro

Global Score
64 vs 70
Hardware Fit
41 vs 73
Quality Score
74 vs 68

Hardware

gemma4:31b llama3.1:8b-instru…
MachineSystem manufacturer—
CPUAMD Ryzen 9 5950X 16-Core ProcessorC1-Pro
Cores320
RAM32 GB11 GB
GPUNVIDIA GeForce RTX 3090Integrated / Unknown
OSMicrosoft Windows 11 Pro 10.0.26300unknown unknown
Archx64arm64
Power Modebalancedunknown

Performance

gemma4:31b llama3.1:8b-instru…
Tokens/sec9.56.5
First chunk1751 ms950 ms
TTFT30.0 s950 ms
Load time33.9 s11.5 s
Memory usage1.4 GB4.4 GB
Memory %4%38%

HW Fit Score Breakdown

gemma4:31b

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

llama3.1:8b-instruct-q4…

Speed
25/50
TTFT
20/20
Memory
28/30

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

llama3.1:8b-instruct-q4…

Reasoning
11/20
Coding
17/20
Instruction
11/20
Structured
14/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate 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