hf.co/empero-ai/Qwen3.8-2B-Distill-GGUF:BF16
OLLAMA GGUFqwen35 · 1.94B · BF16
Aug 26, 2026 · Apple M1 Pro
qwen2.5-coder:7b
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K
Global Score
66 vs 68
Hardware Fit
100 vs 59
Quality Score
52 vs 72
Hardware
hf.co/empero-ai/Qw… qwen2.5-coder:7b
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… qwen2.5-coder:7b
Tokens/sec40.234.4
First chunk101 ms1991 ms
TTFT101 ms2.0 s
Load time2.6 s40.6 s
Memory usage4.7 GB5.0 GB
Memory %30%8%
HW Fit Score Breakdown
hf.co/empero-ai/Qwen3.8…
Speed
50/50
TTFT
20/20
Memory
30/30
qwen2.5-coder:7b
Speed
38/50
TTFT
12/20
Memory
9/30
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
qwen2.5-coder:7b
Reasoning
11/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
9/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate 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