Back to leaderboard

qwen3.5-9b

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Excellent

Mar 3, 2026 · Apple M4

llama3.2:3b

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Jun 25, 2026 · Cortex-A78AE

Global Score
81 vs 74
Hardware Fit
84 vs 99
Quality Score
79 vs 63

Hardware

qwen3.5-9b llama3.2:3b
MachineMacBook AirNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M4Cortex-A78AE
Cores106
RAM32 GB7 GB
GPUApple M4Integrated / Unknown
OSmacOS 26.3Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5-9b llama3.2:3b
Tokens/sec20.421.1
First chunk3034 ms1032 ms
TTFT3.0 s1.0 s
Load timeN/A8.4 s
Memory usage5.6 GB2.4 GB
Memory %17%32%

HW Fit Score Breakdown

qwen3.5-9b

Speed
41/50
TTFT
14/20
Memory
29/30

llama3.2:3b

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

Quality

qwen3.5-9b

Reasoning
14/20
Coding
15/20
Instruction
15/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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 qwen3.5-9b 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