richardyoung/qwythos-9b-abliterated:Q8_0
OLLAMA GGUFqwen35 · 9.0B · Q8_0
Jun 28, 2026 · Apple M4 Pro
qwen3.6:35b-mlx
OLLAMA GGUFnvfp4
Jul 17, 2026 · Apple M5 Max
Global Score
65 vs 80
Hardware Fit
96 vs 77
Quality Score
52 vs 81
Hardware
richardyoung/qwyth… qwen3.6:35b-mlx
MachineMac miniMacBook Pro
CPUApple M4 ProApple M5 Max
Cores1218
RAM24 GB48 GB
GPUApple M4 ProApple M5 Max
OSmacOS 15.6.1macOS 26.5.2
Archarm64arm64
Power Modebalancedbalanced
Performance
richardyoung/qwyth… qwen3.6:35b-mlx
Tokens/sec25.3129.8
First chunk397 ms77 ms
TTFT397 ms30.0 s
Load time6.3 s1.8 s
Memory usage8.3 GB19.7 GB
Memory %34%41%
HW Fit Score Breakdown
richardyoung/qwythos-9b…
Speed
47/50
TTFT
20/20
Memory
29/30
qwen3.6:35b-mlx
Speed
50/50
TTFT
0/20
Memory
27/30
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
qwen3.6:35b-mlx
Reasoning
19/20
Coding
9/20
Instruction
18/20
Structured
11/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Strong Structured Output: Adequate 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