qwen3:0.6b
OLLAMA GGUFqwen3 · 751.63M · Q4_K_M
Apr 29, 2026 · Intel Core™ i5-8350U
hf.co/empero-ai/Qwen3.8-2B-Distill-GGUF:BF16
OLLAMA GGUFqwen35 · 1.94B · BF16
Aug 22, 2026 · Apple M1 Pro
Global Score
61 vs 66
Hardware Fit
85 vs 100
Quality Score
51 vs 52
Hardware
qwen3:0.6b hf.co/empero-ai/Qw…
MachineLENOVO 20L7CTO1WWMacBook Pro
CPUIntel Core™ i5-8350UApple M1 Pro
Cores810
RAM23 GB16 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Apple M1 Pro
OSFedora Linux 43macOS 26.6.2
Archx64arm64
Power Modelow-powerbalanced
Performance
qwen3:0.6b hf.co/empero-ai/Qw…
Tokens/sec27.040.2
First chunk597 ms325 ms
TTFT8.7 s325 ms
Load time1.8 s3.1 s
Memory usage0.9 GB4.7 GB
Memory %4%30%
HW Fit Score Breakdown
qwen3:0.6b
Speed
50/50
TTFT
5/20
Memory
30/30
hf.co/empero-ai/Qwen3.8…
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
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
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
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