Back to leaderboard

qwen3.8-27b-mlx

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Marginal

Aug 17, 2026 · Apple M5 Max

cogito:3b

OLLAMA GGUF

llama · 3.6B · Q4_K_M

Good

Mar 6, 2026 · Apple M4

Global Score
59 vs 67
Hardware Fit
63 vs 100
Quality Score
58 vs 53

Hardware

qwen3.8-27b-mlx cogito:3b
MachineMacBook ProMacBook Air
CPUApple M5 MaxApple M4
Cores1810
RAM64 GB32 GB
GPUApple M5 MaxApple M4
OSmacOS 27.0macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.8-27b-mlx cogito:3b
Tokens/sec18.345.6
First chunk4 ms177 ms
TTFT530 ms177 ms
Load timeN/A0.8 s
Memory usage38.5 GB7.0 GB
Memory %60%22%

HW Fit Score Breakdown

qwen3.8-27b-mlx

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

cogito:3b

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

Quality

qwen3.8-27b-mlx

Reasoning
19/20
Coding
14/20
Instruction
6/20
Structured
1/15
Math
13/15
Multilingual
5/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak

cogito:3b

Reasoning
6/20
Coding
8/20
Instruction
13/20
Structured
15/15
Math
2/15
Multilingual
9/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
View qwen3.8-27b-mlx details | View cogito:3b 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