Back to leaderboard

llama3.2:3b

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Mar 5, 2026 · Intel Core™ i5-6500

Global Score
67 vs 61
Hardware Fit
77 vs 69
Quality Score
63 vs 58

Hardware

llama3.2:3b qwen3.5:4b
MachineLENOVO 20U30029MBGigabyte Technology Co., Ltd. H170M-D3H
CPUIntel Core™ i5-10210UIntel Core™ i5-6500
Cores84
RAM15 GB16 GB
GPUCometLake-U GT2 [UHD Graphics]GP104 [GeForce GTX 1070]
OSPop 24.04 LTSUbuntu 24.04.4 LTS
Archx64x64
Power Modelow-powerlow-power

Performance

llama3.2:3b qwen3.5:4b
Tokens/sec10.035.7
First chunk1166 ms438 ms
TTFT1.2 s5.1 s
Load time6.8 s40.1 s
Memory usage3.8 GB5.5 GB
Memory %25%35%

HW Fit Score Breakdown

llama3.2:3b

Speed
27/50
TTFT
20/20
Memory
30/30

qwen3.5:4b

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

Quality

llama3.2:3b

Reasoning
11/20
Coding
15/20
Instruction
13/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong

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

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