neural-chat:7b
OLLAMA GGUFllama · 7B · Q4_0
Mar 2, 2026 · Apple M4
codestral:22b
OLLAMA GGUFllama · 22.2B · Q4_0
Jun 26, 2026 · Cortex-X925
Global Score
67 vs 67
Hardware Fit
96 vs 67
Quality Score
55 vs 67
Hardware
neural-chat:7b codestral:22b
MachineMacBook AirNVIDIA NVIDIA_DGX_Spark
CPUApple M4Cortex-X925
Cores1020
RAM32 GB122 GB
GPUApple M4Device 2e12
OSmacOS 26.3Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance
Performance
neural-chat:7b codestral:22b
Tokens/sec22.517.2
First chunkN/A129 ms
TTFT242 ms129 ms
Load time0.4 s11.6 s
Memory usage4.5 GB18.9 GB
Memory %14%16%
HW Fit Score Breakdown
neural-chat:7b
Speed
36/50
TTFT
30/20
Memory
30/30
codestral:22b
Speed
17/50
TTFT
20/20
Memory
30/30
Quality
neural-chat:7b
Reasoning
7/20
Coding
9/20
Instruction
12/20
Structured
12/15
Math
7/15
Multilingual
8/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak 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$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest