Back to leaderboard

qwen/qwen3-8b

LM-STUDIO MLX

qwen3 · 8B · 4bit

Excellent

Mar 5, 2026 · Apple M4 Pro

llama3.2:3b

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Jun 25, 2026 · Cortex-A78AE

Global Score
89 vs 74
Hardware Fit
95 vs 99
Quality Score
87 vs 63

Hardware

qwen/qwen3-8b llama3.2:3b
MachineMac miniNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M4 ProCortex-A78AE
Cores146
RAM64 GB7 GB
GPUApple M4 ProIntegrated / Unknown
OSmacOS 15.7.4Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen/qwen3-8b llama3.2:3b
Tokens/sec33.421.1
First chunk257 ms1032 ms
TTFT257 ms1.0 s
Load timeN/A8.4 s
Memory usage4.3 GB2.4 GB
Memory %7%32%

HW Fit Score Breakdown

qwen/qwen3-8b

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

llama3.2:3b

Speed
50/50
TTFT
20/20
Memory
29/30

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

llama3.2:3b

Reasoning
10/20
Coding
14/20
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 llama3.2:3b 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