Back to leaderboard

qwen3.8-27b-mlx

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Marginal

Aug 17, 2026 · Apple M5 Max

starling-lm:7b

OLLAMA GGUF

llama · 7B · Q4_0

Good

Mar 6, 2026 · Apple M4

Global Score
59 vs 65
Hardware Fit
63 vs 96
Quality Score
58 vs 52

Hardware

qwen3.8-27b-mlx starling-lm:7b
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 starling-lm:7b
Tokens/sec18.323.8
First chunk4 ms232 ms
TTFT530 ms232 ms
Load timeN/A0.4 s
Memory usage38.5 GB5.3 GB
Memory %60%17%

HW Fit Score Breakdown

qwen3.8-27b-mlx

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

starling-lm:7b

Speed
46/50
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

starling-lm:7b

Reasoning
10/20
Coding
13/20
Instruction
8/20
Structured
3/15
Math
9/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Adequate Multilingual: Strong
View qwen3.8-27b-mlx details | View starling-lm:7b 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