Back to leaderboard

qwen3.8-27b-mlx

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Marginal

Aug 17, 2026 · Apple M5 Max

mistral:latest

OLLAMA GGUF

llama · 7.2B · Q4_K_M

Good

Mar 2, 2026 · Apple M4

Global Score
59 vs 73
Hardware Fit
63 vs 96
Quality Score
58 vs 63

Hardware

qwen3.8-27b-mlx mistral:latest
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 mistral:latest
Tokens/sec18.322.5
First chunk4 msN/A
TTFT530 ms257 ms
Load timeN/A0.6 s
Memory usage38.5 GB10.1 GB
Memory %60%32%

HW Fit Score Breakdown

qwen3.8-27b-mlx

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

mistral:latest

Speed
36/50
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

mistral:latest

Reasoning
8/20
Coding
12/20
Instruction
15/20
Structured
14/15
Math
5/15
Multilingual
9/10
Reasoning: Weak Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak 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