codestral:22b
OLLAMA GGUFllama · 22.2B · Q4_0
Jun 26, 2026 · Cortex-X925
nemotron-3-nano:4b
OLLAMA GGUFnemotron_h · 4.0B · Q4_K_M
Aug 26, 2026 · Apple M1 Pro
Global Score
67 vs 93
Hardware Fit
67 vs 95
Quality Score
67 vs 92
Hardware
codestral:22b nemotron-3-nano:4b
MachineNVIDIA NVIDIA_DGX_SparkMacBook Pro
CPUCortex-X925Apple M1 Pro
Cores2010
RAM122 GB16 GB
GPUDevice 2e12Apple M1 Pro
OSUbuntu 24.04.4 LTSmacOS 26.6.2
Archarm64arm64
Power Modeperformancebalanced
Performance
codestral:22b nemotron-3-nano:4b
Tokens/sec17.231.7
First chunk129 ms270 ms
TTFT129 ms2.9 s
Load time11.6 s2.1 s
Memory usage18.9 GB4.1 GB
Memory %16%25%
HW Fit Score Breakdown
codestral:22b
Speed
17/50
TTFT
20/20
Memory
30/30
nemotron-3-nano:4b
Speed
50/50
TTFT
15/20
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
nemotron-3-nano:4b
Reasoning
18/20
Coding
17/20
Instruction
17/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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