Back to leaderboard

hf.co/empero-ai/Qwen3.8-2B-Distill-GGUF:BF16

OLLAMA GGUF

qwen35 · 1.94B · BF16

Good

Aug 22, 2026 · Apple M1 Pro

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Good

Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K

Global Score
66 vs 77
Hardware Fit
100 vs 75
Quality Score
52 vs 78

Hardware

hf.co/empero-ai/Qw… qwen3.5:9b
MachineMacBook ProASUS
CPUApple M1 ProIntel Gen Intel® Core™ i7-13700K
Cores1024
RAM16 GB64 GB
GPUApple M1 ProNVIDIA GeForce RTX 3070
OSmacOS 26.6.2Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedunknown

Performance

hf.co/empero-ai/Qw… qwen3.5:9b
Tokens/sec40.230.5
First chunk325 ms291 ms
TTFT325 ms291 ms
Load time3.1 s4.8 s
Memory usage4.7 GB8.8 GB
Memory %30%14%

HW Fit Score Breakdown

hf.co/empero-ai/Qwen3.8…

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

qwen3.5:9b

Speed
34/50
TTFT
20/20
Memory
21/30

Quality

hf.co/empero-ai/Qwen3.8…

Reasoning
15/20
Coding
9/20
Instruction
8/20
Structured
1/15
Math
15/15
Multilingual
4/10
Reasoning: Adequate Coding: Weak Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak

qwen3.5:9b

Reasoning
14/20
Coding
15/20
Instruction
14/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View hf.co/empero-ai/Qw… details | View qwen3.5:9b 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