hf.co/empero-ai/Qwen3.8-2B-Distill-GGUF:BF16
OLLAMA GGUFqwen35 · 1.94B · BF16
Aug 23, 2026 · Apple M1 Pro
richardyoung/qwythos-9b-abliterated:Q8_0
OLLAMA GGUFqwen35 · 9.0B · Q8_0
Jun 28, 2026 · Apple M4 Pro
Global Score
66 vs 65
Hardware Fit
100 vs 96
Quality Score
52 vs 52
Hardware
hf.co/empero-ai/Qw… richardyoung/qwyth…
MachineMacBook ProMac mini
CPUApple M1 ProApple M4 Pro
Cores1012
RAM16 GB24 GB
GPUApple M1 ProApple M4 Pro
OSmacOS 26.6.2macOS 15.6.1
Archarm64arm64
Power Modebalancedbalanced
Performance
hf.co/empero-ai/Qw… richardyoung/qwyth…
Tokens/sec40.425.3
First chunk93 ms397 ms
TTFT93 ms397 ms
Load time2.7 s6.3 s
Memory usage4.7 GB8.3 GB
Memory %30%34%
HW Fit Score Breakdown
hf.co/empero-ai/Qwen3.8…
Speed
50/50
TTFT
20/20
Memory
30/30
richardyoung/qwythos-9b…
Speed
47/50
TTFT
20/20
Memory
29/30
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
richardyoung/qwythos-9b…
Reasoning
18/20
Coding
13/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
1/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest