hf.co/empero-ai/Qwen3.8-2B-Distill-GGUF:BF16
OLLAMA GGUFqwen35 · 1.94B · BF16
Aug 25, 2026 · Apple M1 Pro
qwen3:0.6b
OLLAMA GGUFqwen3 · 751.63M · Q4_K_M
Apr 29, 2026 · Intel Core™ i5-8350U
Global Score
76 vs 61
Hardware Fit
100 vs 85
Quality Score
66 vs 51
Hardware
hf.co/empero-ai/Qw… qwen3:0.6b
MachineMacBook ProLENOVO 20L7CTO1WW
CPUApple M1 ProIntel Core™ i5-8350U
Cores108
RAM16 GB23 GB
GPUApple M1 ProKaby Lake-R GT2 [UHD Graphics 620]
OSmacOS 26.6.2Fedora Linux 43
Archarm64x64
Power Modebalancedlow-power
Performance
hf.co/empero-ai/Qw… qwen3:0.6b
Tokens/sec40.327.0
First chunk101 ms597 ms
TTFT101 ms8.7 s
Load time2.7 s1.8 s
Memory usage4.5 GB0.9 GB
Memory %28%4%
HW Fit Score Breakdown
hf.co/empero-ai/Qwen3.8…
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3:0.6b
Speed
50/50
TTFT
5/20
Memory
30/30
Quality
hf.co/empero-ai/Qwen3.8…
Reasoning
11/20
Coding
10/20
Instruction
12/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
qwen3:0.6b
Reasoning
14/20
Coding
0/20
Instruction
9/20
Structured
12/15
Math
9/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Strong Math: Adequate Multilingual: Adequate
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