Back to leaderboard

mlx-community/meta-llama-3.1-8b-instruct

LM-STUDIO MLX

llama · 8B · 4bit

Good

Mar 5, 2026 · Apple M4 Pro

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Aug 22, 2026 · Apple M1 Pro

Global Score
77 vs 69
Hardware Fit
100 vs 85
Quality Score
67 vs 62

Hardware

mlx-community/meta… qwen3.5:4b
MachineMac miniMacBook Pro
CPUApple M4 ProApple M1 Pro
Cores1410
RAM64 GB16 GB
GPUApple M4 ProApple M1 Pro
OSmacOS 15.7.4macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced

Performance

mlx-community/meta… qwen3.5:4b
Tokens/sec54.336.9
First chunk277 ms474 ms
TTFT277 ms6.9 s
Load timeN/A2.9 s
Memory usage4.2 GB5.3 GB
Memory %7%33%

HW Fit Score Breakdown

mlx-community/meta-llam…

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

qwen3.5:4b

Speed
50/50
TTFT
6/20
Memory
29/30

Quality

mlx-community/meta-llam…

Reasoning
11/20
Coding
14/20
Instruction
14/20
Structured
15/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor 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
View mlx-community/meta… details | View qwen3.5:4b details

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