qwen3.8:27b
OLLAMA GGUFqwen35 · 27.3B · Q4_K_M
Oct 3, 2026 · Cortex-X925
hf.co/empero-ai/Qwen3.8-2B-Distill-GGUF:BF16
OLLAMA GGUFqwen35 · 1.94B · BF16
Aug 25, 2026 · Apple M1 Pro
Global Score
84 vs 76
Hardware Fit
66 vs 100
Quality Score
92 vs 66
Hardware
qwen3.8:27b hf.co/empero-ai/Qw…
MachineNVIDIA NVIDIA_DGX_SparkMacBook Pro
CPUCortex-X925Apple M1 Pro
Cores2010
RAM122 GB16 GB
GPUDevice 2e12Apple M1 Pro
OSUbuntu 24.04.5 LTSmacOS 26.6.2
Archarm64arm64
Power Modeperformancebalanced
Performance
qwen3.8:27b hf.co/empero-ai/Qw…
Tokens/sec29.440.3
First chunk306 ms101 ms
TTFT4.8 s101 ms
Load time5.3 s2.7 s
Memory usage16.2 GB4.5 GB
Memory %13%28%
HW Fit Score Breakdown
qwen3.8:27b
Speed
31/50
TTFT
5/20
Memory
30/30
hf.co/empero-ai/Qwen3.8…
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
qwen3.8:27b
Reasoning
19/20
Coding
19/20
Instruction
14/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
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
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