Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Mar 5, 2026 · Intel Core™ i5-6500

qwen3-coder:latest

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Good

May 24, 2026 · Intel Gen Intel® Core™ i7-1355U

Global Score
61 vs 76
Hardware Fit
69 vs 51
Quality Score
58 vs 87

Hardware

qwen3.5:4b qwen3-coder:latest
MachineGigabyte Technology Co., Ltd. H170M-D3HDell Inc. Inspiron 15 3530
CPUIntel Core™ i5-6500Intel Gen Intel® Core™ i7-1355U
Cores412
RAM16 GB31 GB
GPUGP104 [GeForce GTX 1070]Raptor Lake-P [Iris Xe Graphics]
OSUbuntu 24.04.4 LTScachyos rolling
Archx64x64
Power Modelow-powerlow-power

Performance

qwen3.5:4b qwen3-coder:latest
Tokens/sec35.77.6
First chunk438 ms2037 ms
TTFT5.1 s2.0 s
Load time40.1 s8.7 s
Memory usage5.5 GB18.9 GB
Memory %35%61%

HW Fit Score Breakdown

qwen3.5:4b

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

qwen3-coder:latest

Speed
13/50
TTFT
18/20
Memory
20/30

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

qwen3-coder:latest

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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