Back to leaderboard

llama3.2:latest

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Feb 28, 2026 · Apple M4 Pro

codestral:22b

OLLAMA GGUF

llama · 22.2B · Q4_0

Good

Jun 26, 2026 · Cortex-X925

Global Score
73 vs 67
Hardware Fit
100 vs 67
Quality Score
61 vs 67

Hardware

llama3.2:latest codestral:22b
MachineMac MiniNVIDIA NVIDIA_DGX_Spark
CPUApple M4 ProCortex-X925
Cores1420
RAM64 GB122 GB
GPUApple M4 ProDevice 2e12
OSmacOS 15.7.4Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modeunknownperformance

Performance

llama3.2:latest codestral:22b
Tokens/sec98.917.2
First chunkN/A129 ms
TTFT125 ms129 ms
Load time2.3 s11.6 s
Memory usage22.1 GB18.9 GB
Memory %35%16%

HW Fit Score Breakdown

llama3.2:latest

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

codestral:22b

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

Quality

llama3.2:latest

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