Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Mar 5, 2026 · Intel Core™ i5-6500

llama3.2:3b

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Jun 25, 2026 · Cortex-A78AE

Global Score
61 vs 74
Hardware Fit
69 vs 99
Quality Score
58 vs 63

Hardware

qwen3.5:4b llama3.2:3b
MachineGigabyte Technology Co., Ltd. H170M-D3HNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUIntel Core™ i5-6500Cortex-A78AE
Cores46
RAM16 GB7 GB
GPUGP104 [GeForce GTX 1070]Integrated / Unknown
OSUbuntu 24.04.4 LTSUbuntu 22.04.5 LTS
Archx64arm64
Power Modelow-powerbalanced

Performance

qwen3.5:4b llama3.2:3b
Tokens/sec35.721.1
First chunk438 ms1032 ms
TTFT5.1 s1.0 s
Load time40.1 s8.4 s
Memory usage5.5 GB2.4 GB
Memory %35%32%

HW Fit Score Breakdown

qwen3.5:4b

Speed
50/50
TTFT
11/20
Memory
8/30

llama3.2:3b

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

Quality

qwen3.5:4b

Reasoning
18/20
Coding
1/20
Instruction
8/20
Structured
8/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Adequate 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

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