Back to leaderboard

qwen3.8-27b-mlx

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Marginal

Aug 17, 2026 · Apple M5 Max

qwen3:1.7b

OLLAMA GGUF

qwen3 · 2.0B · Q4_K_M

Good

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

Global Score
59 vs 72
Hardware Fit
63 vs 92
Quality Score
58 vs 63

Hardware

qwen3.8-27b-mlx qwen3:1.7b
MachineMacBook ProAZW GTR Pro
CPUApple M5 MaxAMD RYZEN AI MAX+ 395
Cores1832
RAM64 GB125 GB
GPUApple M5 MaxAMD Radeon 8060S
OSmacOS 27.0Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedlow-power

Performance

qwen3.8-27b-mlx qwen3:1.7b
Tokens/sec18.3120.7
First chunk4 ms93 ms
TTFT530 ms1.5 s
Load timeN/A2.5 s
Memory usage38.5 GB5.8 GB
Memory %60%5%

HW Fit Score Breakdown

qwen3.8-27b-mlx

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

qwen3:1.7b

Speed
50/50
TTFT
12/20
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

qwen3:1.7b

Reasoning
13/20
Coding
6/20
Instruction
13/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate 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