Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

qwen3:14b

OLLAMA GGUF

qwen3 · 14.8B · Q4_K_M

Excellent

Jun 13, 2026 · AMD Ryzen 9 3900X 12-Core Processor

Global Score
64 vs 82
Hardware Fit
69 vs 90
Quality Score
62 vs 79

Hardware

qwen3.5:4b qwen3:14b
MachineLENOVO 20U30029MBMicro-Star International Co., Ltd. MS-7C37
CPUIntel Core™ i5-10210UAMD Ryzen 9 3900X 12-Core Processor
Cores824
RAM15 GB64 GB
GPUCometLake-U GT2 [UHD Graphics]GameViewer Virtual Display Adapter, NVIDIA GeForce RTX 3080
OSPop 24.04 LTSMicrosoft Windows 11 专业版 10.0.26200
Archx64x64
Power Modeperformancebalanced

Performance

qwen3.5:4b qwen3:14b
Tokens/sec7.474.4
First chunk1815 ms324 ms
TTFT1.8 s2.6 s
Load time10.9 s5.1 s
Memory usage3.5 GB9.0 GB
Memory %23%14%

HW Fit Score Breakdown

qwen3.5:4b

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

qwen3:14b

Speed
50/50
TTFT
10/20
Memory
30/30

Quality

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

qwen3:14b

Reasoning
18/20
Coding
11/20
Instruction
17/20
Structured
14/15
Math
10/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.5:4b details | View qwen3:14b 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