qwen3:8b
OLLAMA GGUFqwen3 · 8.2B · Q4_K_M
Mar 5, 2026 · Intel Core™ Ultra 9 285K
hf.co/empero-ai/Qwen3.8-2B-Distill-GGUF:BF16
OLLAMA GGUFqwen35 · 1.94B · BF16
Aug 22, 2026 · Apple M1 Pro
Global Score
84 vs 66
Hardware Fit
97 vs 100
Quality Score
79 vs 52
Hardware
qwen3:8b hf.co/empero-ai/Qw…
MachineASUSMacBook Pro
CPUIntel Core™ Ultra 9 285KApple M1 Pro
Cores2410
RAM47 GB16 GB
GPUNVIDIA GeForce RTX 5090, Intel(R) GraphicsApple M1 Pro
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.6.2
Archx64arm64
Power Modebalancedbalanced
Performance
qwen3:8b hf.co/empero-ai/Qw…
Tokens/sec208.040.2
First chunk82 ms325 ms
TTFT1.3 s325 ms
Load time1.5 s3.1 s
Memory usage9.6 GB4.7 GB
Memory %20%30%
HW Fit Score Breakdown
qwen3:8b
Speed
50/50
TTFT
18/20
Memory
29/30
hf.co/empero-ai/Qwen3.8…
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
qwen3:8b
Reasoning
18/20
Coding
10/20
Instruction
14/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
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