Back to leaderboard

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

LM-STUDIO MLX

llama · 8B · 4bit

Good

Mar 5, 2026 · Apple M4 Pro

qwen/qwen3.6-27b

LM-STUDIO MLX

qwen3_5 · 27B · 4bit

Excellent

Oct 22, 2026 · Apple M1 Pro

Global Score
77 vs 80
Hardware Fit
100 vs 56
Quality Score
67 vs 90

Hardware

mlx-community/meta… qwen/qwen3.6-27b
MachineMac miniMacBook Pro
CPUApple M4 ProApple M1 Pro
Cores1410
RAM64 GB32 GB
GPUApple M4 ProApple M1 Pro
OSmacOS 15.7.4macOS 15.6.1
Archarm64arm64
Power Modebalancedbalanced

Performance

mlx-community/meta… qwen/qwen3.6-27b
Tokens/sec54.310.8
First chunk277 ms16 ms
TTFT277 ms2.6 s
Load timeN/AN/A
Memory usage4.2 GB21.0 GB
Memory %7%66%

HW Fit Score Breakdown

mlx-community/meta-llam…

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

qwen/qwen3.6-27b

Speed
23/50
TTFT
16/20
Memory
17/30

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

qwen/qwen3.6-27b

Reasoning
18/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View mlx-community/meta… details | View qwen/qwen3.6-27b 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