hf.co/empero-ai/Qwen3.8-2B-Distill-GGUF:BF16
OLLAMA GGUFqwen35 · 1.94B · BF16
Aug 26, 2026 · Apple M1 Pro
qwen3.8:27b-bf16
OLLAMA GGUFqwen35 · 27.3B · BF16
Aug 22, 2026 · AMD EPYC 7713 64-Core Processor
Global Score
66 vs 85
Hardware Fit
100 vs 77
Quality Score
52 vs 88
Hardware
hf.co/empero-ai/Qw… qwen3.8:27b-bf16
MachineMacBook ProDell Inc. PowerEdge XE8545
CPUApple M1 ProAMD EPYC 7713 64-Core Processor
Cores10128
RAM16 GB1007 GB
GPUApple M1 ProGA100 [A100 SXM4 80GB], GA100 [A100 SXM4 80GB], Integrated Matrox G200eW3 Graphics Controller, GA100 [A100 SXM4 80GB], GA100 [A100 SXM4 80GB]
OSmacOS 26.6.2Rocky Linux 8.10
Archarm64x64
Power Modebalancedunknown
Performance
hf.co/empero-ai/Qw… qwen3.8:27b-bf16
Tokens/sec40.227.2
First chunk101 ms237 ms
TTFT101 ms237 ms
Load time2.6 s43.8 s
Memory usage4.7 GB68.8 GB
Memory %30%7%
HW Fit Score Breakdown
hf.co/empero-ai/Qwen3.8…
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3.8:27b-bf16
Speed
27/50
TTFT
20/20
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
qwen3.8:27b-bf16
Reasoning
18/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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