Back to leaderboard

llama3.2:latest

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

May 27, 2026 · AMD Ryzen 5 2600X Six-Core Processor

qwen3.8-27b-mlx

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Marginal

Aug 17, 2026 · Apple M5 Max

Global Score
76 vs 59
Hardware Fit
100 vs 63
Quality Score
65 vs 58

Hardware

llama3.2:latest qwen3.8-27b-mlx
MachineMicro-Star International Co., Ltd. MS-7B79MacBook Pro
CPUAMD Ryzen 5 2600X Six-Core ProcessorApple M5 Max
Cores1218
RAM16 GB64 GB
GPUNVIDIA GeForce GTX 1080Apple M5 Max
OSMicrosoft Windows 11 Famille 10.0.26200macOS 27.0
Archx64arm64
Power Modebalancedbalanced

Performance

llama3.2:latest qwen3.8-27b-mlx
Tokens/sec57.018.3
First chunk264 ms4 ms
TTFT264 ms530 ms
Load time9.7 sN/A
Memory usage2.6 GB38.5 GB
Memory %16%60%

HW Fit Score Breakdown

llama3.2:latest

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

qwen3.8-27b-mlx

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

Quality

llama3.2:latest

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

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

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