Back to leaderboard

codestral:22b

OLLAMA GGUF

llama · 22.2B · Q4_0

Good

Jun 26, 2026 · Cortex-X925

gemma3:1b

OLLAMA GGUF

gemma3 · 999.89M · Q4_K_M

Good

Feb 28, 2026 · Apple M4

Global Score
67 vs 68
Hardware Fit
67 vs 98
Quality Score
67 vs 55

Hardware

codestral:22b gemma3:1b
MachineNVIDIA NVIDIA_DGX_SparkMacBook Air
CPUCortex-X925Apple M4
Cores2010
RAM122 GB32 GB
GPUDevice 2e12Apple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archarm64arm64
Power Modeperformanceunknown

Performance

codestral:22b gemma3:1b
Tokens/sec17.239.4
First chunk129 msN/A
TTFT129 ms362 ms
Load time11.6 s0.3 s
Memory usage18.9 GB1.3 GB
Memory %16%4%

HW Fit Score Breakdown

codestral:22b

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

gemma3:1b

Speed
40/50
TTFT
30/20
Memory
28/30

Quality

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

gemma3:1b

Reasoning
6/20
Coding
13/20
Instruction
15/20
Structured
12/15
Math
1/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Strong 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