Back to leaderboard

llama3.1:8b-instruct-q4_K_S

OLLAMA GGUF

llama · 8.0B · Q4_K_S

Good

Nov 22, 2026 · C1-Pro

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Aug 23, 2026 · Apple M1 Pro

Global Score
70 vs 69
Hardware Fit
73 vs 86
Quality Score
68 vs 62

Hardware

llama3.1:8b-instru… qwen3.5:4b
Machine—MacBook Pro
CPUC1-ProApple M1 Pro
Cores010
RAM11 GB16 GB
GPUIntegrated / UnknownApple M1 Pro
OSunknown unknownmacOS 26.6.2
Archarm64arm64
Power Modeunknownbalanced

Performance

llama3.1:8b-instru… qwen3.5:4b
Tokens/sec6.536.7
First chunk950 ms207 ms
TTFT950 ms6.6 s
Load time11.5 s3.0 s
Memory usage4.4 GB5.3 GB
Memory %38%33%

HW Fit Score Breakdown

llama3.1:8b-instruct-q4…

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

qwen3.5:4b

Speed
50/50
TTFT
7/20
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

qwen3.5:4b

Reasoning
16/20
Coding
1/20
Instruction
14/20
Structured
9/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Strong 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