richardyoung/qwythos-9b-abliterated:Q8_0
OLLAMA GGUFqwen35 · 9.0B · Q8_0
Jun 28, 2026 · Apple M4 Pro
qwen3.5:35b-a3b
OLLAMA GGUFqwen35moe · 36.0B · Q4_K_M
Mar 6, 2026 · Apple M4 Pro
Global Score
65 vs 59
Hardware Fit
96 vs 69
Quality Score
52 vs 54
Hardware
richardyoung/qwyth… qwen3.5:35b-a3b
MachineMac miniMacBook Pro
CPUApple M4 ProApple M4 Pro
Cores1214
RAM24 GB48 GB
GPUApple M4 ProApple M4 Pro
OSmacOS 15.6.1macOS 26.3.1
Archarm64arm64
Power Modebalancedbalanced
Performance
richardyoung/qwyth… qwen3.5:35b-a3b
Tokens/sec25.330.5
First chunk397 ms333 ms
TTFT397 ms30.0 s
Load time6.3 s9.8 s
Memory usage8.3 GB25.1 GB
Memory %34%52%
HW Fit Score Breakdown
richardyoung/qwythos-9b…
Speed
47/50
TTFT
20/20
Memory
29/30
qwen3.5:35b-a3b
Speed
45/50
TTFT
0/20
Memory
24/30
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
qwen3.5:35b-a3b
Reasoning
18/20
Coding
1/20
Instruction
7/20
Structured
6/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Weak 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