Back to leaderboard

llama3.1:8b-instruct-q4_K_S

OLLAMA GGUF

llama · 8.0B · Q4_K_S

Good

Nov 22, 2026 · C1-Pro

cogito:8b

OLLAMA GGUF

llama · 8.0B · Q4_K_M

Good

Mar 6, 2026 · Apple M4

Global Score
70 vs 77
Hardware Fit
73 vs 92
Quality Score
68 vs 70

Hardware

llama3.1:8b-instru… cogito:8b
Machine—MacBook Air
CPUC1-ProApple M4
Cores010
RAM11 GB32 GB
GPUIntegrated / UnknownApple M4
OSunknown unknownmacOS 26.3
Archarm64arm64
Power Modeunknownbalanced

Performance

llama3.1:8b-instru… cogito:8b
Tokens/sec6.521.0
First chunk950 ms312 ms
TTFT950 ms312 ms
Load time11.5 s0.8 s
Memory usage4.4 GB10.4 GB
Memory %38%33%

HW Fit Score Breakdown

llama3.1:8b-instruct-q4…

Speed
25/50
TTFT
20/20
Memory
28/30

cogito:8b

Speed
42/50
TTFT
20/20
Memory
30/30

Quality

llama3.1:8b-instruct-q4…

Reasoning
11/20
Coding
17/20
Instruction
11/20
Structured
14/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

cogito:8b

Reasoning
14/20
Coding
13/20
Instruction
13/20
Structured
15/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate 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