Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Mar 5, 2026 · Intel Core™ i5-6500

qwen3-coder:30b

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Mar 4, 2026 · Intel Gen Intel® Core™ i7-12700K

Global Score
61 vs 80
Hardware Fit
69 vs 60
Quality Score
58 vs 88

Hardware

qwen3.5:4b qwen3-coder:30b
MachineGigabyte Technology Co., Ltd. H170M-D3HASUS
CPUIntel Core™ i5-6500Intel Gen Intel® Core™ i7-12700K
Cores420
RAM16 GB96 GB
GPUGP104 [GeForce GTX 1070]Parsec Virtual Display Adapter, NVIDIA GeForce RTX 2060
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Enterprise 10.0.26200
Archx64x64
Power Modelow-powerbalanced

Performance

qwen3.5:4b qwen3-coder:30b
Tokens/sec35.714.7
First chunk438 ms796 ms
TTFT5.1 s796 ms
Load time40.1 s0.2 s
Memory usage5.5 GB17.9 GB
Memory %35%19%

HW Fit Score Breakdown

qwen3.5:4b

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

qwen3-coder:30b

Speed
14/50
TTFT
19/20
Memory
27/30

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:30b

Reasoning
17/20
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
View qwen3.5:4b details | View qwen3-coder:30b 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