codestral:22b
OLLAMA GGUFllama · 22.2B · Q4_0
Jun 26, 2026 · Cortex-X925
mlx-community/meta-llama-3.1-8b-instruct
LM-STUDIO MLXllama · 8B · 4bit
Mar 5, 2026 · Apple M4 Pro
Global Score
67 vs 77
Hardware Fit
67 vs 100
Quality Score
67 vs 67
Hardware
codestral:22b mlx-community/meta…
MachineNVIDIA NVIDIA_DGX_SparkMac mini
CPUCortex-X925Apple M4 Pro
Cores2014
RAM122 GB64 GB
GPUDevice 2e12Apple M4 Pro
OSUbuntu 24.04.4 LTSmacOS 15.7.4
Archarm64arm64
Power Modeperformancebalanced
Performance
codestral:22b mlx-community/meta…
Tokens/sec17.254.3
First chunk129 ms277 ms
TTFT129 ms277 ms
Load time11.6 sN/A
Memory usage18.9 GB4.2 GB
Memory %16%7%
HW Fit Score Breakdown
codestral:22b
Speed
17/50
TTFT
20/20
Memory
30/30
mlx-community/meta-llam…
Speed
50/50
TTFT
20/20
Memory
30/30
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
mlx-community/meta-llam…
Reasoning
11/20
Coding
14/20
Instruction
14/20
Structured
15/15
Math
4/15
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$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest