Back to leaderboard

qwen3:14b

OLLAMA GGUF

qwen3 · 14.8B · Q4_K_M

Marginal

Mar 5, 2026 · Apple M1 Max

qwen3.5:0.8b

OLLAMA GGUF

qwen35 · 873.44M · Q8_0

Not Rec.

Apr 29, 2026 · Intel Core™ i5-8350U

Global Score
58 vs 18
Hardware Fit
82 vs 53
Quality Score
48 vs 3

Hardware

qwen3:14b qwen3.5:0.8b
MachineMacBook ProLENOVO 20L7CTO1WW
CPUApple M1 MaxIntel Core™ i5-8350U
Cores108
RAM32 GB23 GB
GPUApple M1 MaxKaby Lake-R GT2 [UHD Graphics 620]
OSmacOS 26.3Fedora Linux 43
Archarm64x64
Power Modebalancedlow-power

Performance

qwen3:14b qwen3.5:0.8b
Tokens/sec24.49.4
First chunk294 ms799 ms
TTFT7.9 s30.0 s
Load time3.7 s3.3 s
Memory usage13.8 GB1.9 GB
Memory %43%8%

HW Fit Score Breakdown

qwen3:14b

Speed
47/50
TTFT
5/20
Memory
30/30

qwen3.5:0.8b

Speed
23/50
TTFT
0/20
Memory
30/30

Quality

qwen3:14b

Reasoning
13/20
Coding
6/20
Instruction
10/20
Structured
9/15
Math
2/15
Multilingual
8/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Strong

qwen3.5:0.8b

Reasoning
0/20
Coding
0/20
Instruction
2/20
Structured
0/15
Math
0/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
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