hf.co/empero-ai/Qwen3.8-2B-Distill-GGUF:BF16
OLLAMA GGUFqwen35 · 1.94B · BF16
Aug 22, 2026 · Apple M1 Pro
gptoss · 20.9B · MXFP4
OLLAMA GGUFgptoss · 20.9 · MXFP4
Jul 9, 2026 · Intel Core™ i5-10400
Global Score
66 vs 84
Hardware Fit
100 vs 69
Quality Score
52 vs 91
Hardware
hf.co/empero-ai/Qw… gptoss · 20.9B · M…
MachineMacBook ProMac Pro
CPUApple M1 ProIntel Core™ i5-10400
Cores1012
RAM16 GB32 GB
GPUApple M1 ProAMD Radeon RX 6700 XT
OSmacOS 26.6.2macOS 26.5.1
Archarm64x64
Power Modebalancedbalanced
Performance
hf.co/empero-ai/Qw… gptoss · 20.9B · M…
Tokens/sec40.217.5
First chunk325 ms643 ms
TTFT325 ms7.7 s
Load time3.1 s0.0 s
Memory usage4.7 GB0.8 GB
Memory %30%3%
HW Fit Score Breakdown
hf.co/empero-ai/Qwen3.8…
Speed
50/50
TTFT
20/20
Memory
30/30
gptoss · 20.9B · MXFP4
Speed
34/50
TTFT
5/20
Memory
30/30
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
gptoss · 20.9B · MXFP4
Reasoning
19/20
Coding
19/20
Instruction
13/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
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