Back to leaderboard

qwen3.5:0.8b

OLLAMA GGUF

qwen35 · 873.44M · Q8_0

Not Rec.

Apr 29, 2026 · Intel Core™ i5-8350U

qwen3:14b

OLLAMA GGUF

qwen3 · 14.8B · Q4_K_M

Excellent

Mar 5, 2026 · Apple M1 Max

Global Score
18 vs 90
Hardware Fit
53 vs 97
Quality Score
3 vs 87

Hardware

qwen3.5:0.8b qwen3:14b
MachineLENOVO 20L7CTO1WWMacBook Pro
CPUIntel Core™ i5-8350UApple M1 Max
Cores810
RAM23 GB32 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Apple M1 Max
OSFedora Linux 43macOS 26.3
Archx64arm64
Power Modelow-powerbalanced

Performance

qwen3.5:0.8b qwen3:14b
Tokens/sec9.424.0
First chunk799 ms300 ms
TTFT30.0 s300 ms
Load time3.3 s3.6 s
Memory usage1.9 GB13.8 GB
Memory %8%43%

HW Fit Score Breakdown

qwen3.5:0.8b

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

qwen3:14b

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

Quality

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

qwen3:14b

Reasoning
17/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.5:0.8b 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