Back to leaderboard

qwen3:14b

OLLAMA GGUF

qwen3 · 14.8B · Q4_K_M

Excellent

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

qwen3.5:0.8b

OLLAMA GGUF

qwen35 · 873.44M · Q8_0

Good

Mar 5, 2026 · Apple M1 Max

Global Score
82 vs 62
Hardware Fit
90 vs 100
Quality Score
79 vs 46

Hardware

qwen3:14b qwen3.5:0.8b
MachineMicro-Star International Co., Ltd. MS-7C37MacBook Pro
CPUAMD Ryzen 9 3900X 12-Core ProcessorApple M1 Max
Cores2410
RAM64 GB32 GB
GPUGameViewer Virtual Display Adapter, NVIDIA GeForce RTX 3080Apple M1 Max
OSMicrosoft Windows 11 专业版 10.0.26200macOS 26.3
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3:14b qwen3.5:0.8b
Tokens/sec74.465.8
First chunk324 ms230 ms
TTFT2.6 s230 ms
Load time5.1 s1.5 s
Memory usage9.0 GB2.6 GB
Memory %14%8%

HW Fit Score Breakdown

qwen3:14b

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

qwen3.5:0.8b

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

Quality

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

qwen3.5:0.8b

Reasoning
9/20
Coding
4/20
Instruction
11/20
Structured
13/15
Math
3/15
Multilingual
6/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
View qwen3:14b details | View qwen3.5:0.8b 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