Back to leaderboard

llama3.1:8b-instruct-q4_K_S

OLLAMA GGUF

llama · 8.0B · Q4_K_S

Good

Nov 22, 2026 · C1-Pro

mlx-community/gemma-3-1b-it-8bit

LM-STUDIO GGUF
Good

Mar 5, 2026 · Apple M4

Global Score
70 vs 72
Hardware Fit
73 vs 99
Quality Score
68 vs 61

Hardware

llama3.1:8b-instru… mlx-community/gemm…
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… mlx-community/gemm…
Tokens/sec6.586.3
First chunk950 ms253 ms
TTFT950 ms253 ms
Load time11.5 sN/A
Memory usage4.4 GB1.1 GB
Memory %38%4%

HW Fit Score Breakdown

llama3.1:8b-instruct-q4…

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

mlx-community/gemma-3-1…

Speed
50/50
TTFT
20/20
Memory
29/30

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

mlx-community/gemma-3-1…

Reasoning
7/20
Coding
14/20
Instruction
16/20
Structured
14/15
Math
2/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor 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