Back to leaderboard

qwen/qwen3.8-27b

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Excellent

Aug 18, 2026 · Apple M4 Max

llama3.2:1b

OLLAMA GGUF

llama · 1.2B · Q8_0

Good

Mar 5, 2026 · AMD Ryzen 9 8945HS

Global Score
81 vs 62
Hardware Fit
68 vs 91
Quality Score
87 vs 50

Hardware

qwen/qwen3.8-27b llama3.2:1b
MachineMacBook ProASUSTeK COMPUTER INC. ROG Zephyrus G14 GA403UV_GA403UV
CPUApple M4 MaxAMD Ryzen 9 8945HS
Cores1616
RAM128 GB15 GB
GPUApple M4 MaxNVIDIA GeForce RTX 4060 Laptop GPU, AMD Radeon 780M Graphics
OSmacOS 26.5.2Microsoft Windows 11 Home 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen/qwen3.8-27b llama3.2:1b
Tokens/sec16.4170.2
First chunk5 ms142 ms
TTFT742 ms142 ms
Load timeN/A3.2 s
Memory usage38.5 GB1.6 GB
Memory %30%11%

HW Fit Score Breakdown

qwen/qwen3.8-27b

Speed
18/50
TTFT
20/20
Memory
30/30

llama3.2:1b

Speed
50/50
TTFT
20/20
Memory
21/30

Quality

qwen/qwen3.8-27b

Reasoning
17/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

llama3.2:1b

Reasoning
4/20
Coding
13/20
Instruction
14/20
Structured
13/15
Math
0/15
Multilingual
6/10
Reasoning: Poor Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate

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