Back to leaderboard

qwen/qwen3-8b

LM-STUDIO MLX

qwen3 · 8B · 4bit

Excellent

Mar 5, 2026 · Apple M4 Pro

llama3.2:latest

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

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

Global Score
89 vs 76
Hardware Fit
95 vs 100
Quality Score
87 vs 65

Hardware

qwen/qwen3-8b llama3.2:latest
MachineMac miniMicro-Star International Co., Ltd. MS-7B79
CPUApple M4 ProAMD Ryzen 5 2600X Six-Core Processor
Cores1412
RAM64 GB16 GB
GPUApple M4 ProNVIDIA GeForce GTX 1080
OSmacOS 15.7.4Microsoft Windows 11 Famille 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen/qwen3-8b llama3.2:latest
Tokens/sec33.457.0
First chunk257 ms264 ms
TTFT257 ms264 ms
Load timeN/A9.7 s
Memory usage4.3 GB2.6 GB
Memory %7%16%

HW Fit Score Breakdown

qwen/qwen3-8b

Speed
45/50
TTFT
20/20
Memory
30/30

llama3.2:latest

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

Quality

qwen/qwen3-8b

Reasoning
19/20
Coding
14/20
Instruction
16/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

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
View qwen/qwen3-8b details | View llama3.2:latest details

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