Back to leaderboard

qwen3.8-27b-mlx

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Marginal

Aug 17, 2026 · Apple M5 Max

llama3.2:latest

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Feb 28, 2026 · Apple M4 Pro

Global Score
59 vs 73
Hardware Fit
63 vs 100
Quality Score
58 vs 61

Hardware

qwen3.8-27b-mlx llama3.2:latest
MachineMacBook ProMac Mini
CPUApple M5 MaxApple M4 Pro
Cores1814
RAM64 GB64 GB
GPUApple M5 MaxApple M4 Pro
OSmacOS 27.0macOS 15.7.4
Archarm64arm64
Power Modebalancedunknown

Performance

qwen3.8-27b-mlx llama3.2:latest
Tokens/sec18.398.9
First chunk4 msN/A
TTFT530 ms125 ms
Load timeN/A2.3 s
Memory usage38.5 GB22.1 GB
Memory %60%35%

HW Fit Score Breakdown

qwen3.8-27b-mlx

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

llama3.2:latest

Speed
40/50
TTFT
30/20
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

llama3.2:latest

Reasoning
11/20
Coding
14/20
Instruction
12/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor 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