Back to leaderboard

llama3.1:8b-instruct-q4_K_S

OLLAMA GGUF

llama · 8.0B · Q4_K_S

Good

Nov 22, 2026 · C1-Pro

qwen3.6:35b-mlx

OLLAMA GGUF

nvfp4

Not Rec.

Jul 17, 2026 · Apple M5 Max

Global Score
70 vs 80
Hardware Fit
73 vs 77
Quality Score
68 vs 81

Hardware

llama3.1:8b-instru… qwen3.6:35b-mlx
Machine—MacBook Pro
CPUC1-ProApple M5 Max
Cores018
RAM11 GB48 GB
GPUIntegrated / UnknownApple M5 Max
OSunknown unknownmacOS 26.5.2
Archarm64arm64
Power Modeunknownbalanced

Performance

llama3.1:8b-instru… qwen3.6:35b-mlx
Tokens/sec6.5129.8
First chunk950 ms77 ms
TTFT950 ms30.0 s
Load time11.5 s1.8 s
Memory usage4.4 GB19.7 GB
Memory %38%41%

HW Fit Score Breakdown

llama3.1:8b-instruct-q4…

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

qwen3.6:35b-mlx

Speed
50/50
TTFT
0/20
Memory
27/30

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

qwen3.6:35b-mlx

Reasoning
19/20
Coding
9/20
Instruction
18/20
Structured
11/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Strong 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