qwen3:8b
OLLAMA GGUFqwen3 · 8.2B · Q4_K_M
Aug 15, 2026 · AMD Ryzen 9 3900X 12-Core Processor
richardyoung/qwythos-9b-abliterated:Q8_0
OLLAMA GGUFqwen35 · 9.0B · Q8_0
Jun 28, 2026 · Apple M4 Pro
Global Score
78 vs 65
Hardware Fit
86 vs 96
Quality Score
74 vs 52
Hardware
qwen3:8b richardyoung/qwyth…
Machine—Mac mini
CPUAMD Ryzen 9 3900X 12-Core ProcessorApple M4 Pro
Cores2412
RAM64 GB24 GB
GPUNVIDIA GeForce RTX 4060 TiApple M4 Pro
OSMicrosoft Windows 11 Pro 10.0.26200macOS 15.6.1
Archx64arm64
Power Modebalancedbalanced
Performance
qwen3:8b richardyoung/qwyth…
Tokens/sec48.525.3
First chunk202 ms397 ms
TTFT4.3 s397 ms
Load time4.2 s6.3 s
Memory usage5.5 GB8.3 GB
Memory %9%34%
HW Fit Score Breakdown
qwen3:8b
Speed
50/50
TTFT
6/20
Memory
30/30
richardyoung/qwythos-9b…
Speed
47/50
TTFT
20/20
Memory
29/30
Quality
qwen3:8b
Reasoning
16/20
Coding
8/20
Instruction
14/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
richardyoung/qwythos-9b…
Reasoning
18/20
Coding
13/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
1/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor
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