richardyoung/qwythos-9b-abliterated:Q8_0
OLLAMA GGUFqwen35 · 9.0B · Q8_0
Jun 28, 2026 · Apple M4 Pro
qwen3:30b-a3b-instruct-2507-q4_K_M
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Jul 29, 2026 · Intel Xeon® E5-2637 v3
Global Score
65 vs 83
Hardware Fit
96 vs 66
Quality Score
52 vs 90
Hardware
richardyoung/qwyth… qwen3:30b-a3b-inst…
MachineMac miniDell Inc. Precision Tower 7910
CPUApple M4 ProIntel Xeon® E5-2637 v3
Cores1216
RAM24 GB96 GB
GPUApple M4 ProNVIDIA GeForce RTX 5060 Ti
OSmacOS 15.6.1Microsoft Windows 10 Pro 10.0.19045
Archarm64x64
Power Modebalancedbalanced
Performance
richardyoung/qwyth… qwen3:30b-a3b-inst…
Tokens/sec25.317.7
First chunk397 ms1244 ms
TTFT397 ms1.2 s
Load time6.3 s20.5 s
Memory usage8.3 GB20.6 GB
Memory %34%21%
HW Fit Score Breakdown
richardyoung/qwythos-9b…
Speed
47/50
TTFT
20/20
Memory
29/30
qwen3:30b-a3b-instruct-…
Speed
19/50
TTFT
17/20
Memory
30/30
Quality
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
qwen3:30b-a3b-instruct-…
Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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