Back to leaderboard

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Apr 13, 2026 · Apple M4 Max

codestral:22b

OLLAMA GGUF

llama · 22.2B · Q4_0

Good

Jun 26, 2026 · Cortex-X925

Global Score
76 vs 67
Hardware Fit
46 vs 67
Quality Score
89 vs 67

Hardware

gemma4:31b codestral:22b
MachineMacBook ProNVIDIA NVIDIA_DGX_Spark
CPUApple M4 MaxCortex-X925
Cores1620
RAM64 GB122 GB
GPUApple M4 MaxDevice 2e12
OSmacOS 26.3.1Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance

Performance

gemma4:31b codestral:22b
Tokens/sec22.417.2
First chunk565 ms129 ms
TTFT30.0 s129 ms
Load time6.9 s11.6 s
Memory usage43.9 GB18.9 GB
Memory %69%16%

HW Fit Score Breakdown

gemma4:31b

Speed
30/50
TTFT
0/20
Memory
16/30

codestral:22b

Speed
17/50
TTFT
20/20
Memory
30/30

Quality

gemma4:31b

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

codestral:22b

Reasoning
11/20
Coding
17/20
Instruction
9/20
Structured
14/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Weak 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