Back to leaderboard

llama3.2:3b

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Jun 25, 2026 · Cortex-A78AE

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

Global Score
74 vs 64
Hardware Fit
99 vs 69
Quality Score
63 vs 62

Hardware

llama3.2:3b qwen3.5:4b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperLENOVO 20U30029MB
CPUCortex-A78AEIntel Core™ i5-10210U
Cores68
RAM7 GB15 GB
GPUIntegrated / UnknownCometLake-U GT2 [UHD Graphics]
OSUbuntu 22.04.5 LTSPop 24.04 LTS
Archarm64x64
Power Modebalancedperformance

Performance

llama3.2:3b qwen3.5:4b
Tokens/sec21.17.4
First chunk1032 ms1815 ms
TTFT1.0 s1.8 s
Load time8.4 s10.9 s
Memory usage2.4 GB3.5 GB
Memory %32%23%

HW Fit Score Breakdown

llama3.2:3b

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

qwen3.5:4b

Speed
19/50
TTFT
20/20
Memory
30/30

Quality

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

qwen3.5:4b

Reasoning
15/20
Coding
14/20
Instruction
6/20
Structured
12/15
Math
6/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Weak Multilingual: Strong

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