Back to leaderboard

richardyoung/qwythos-9b-abliterated:Q8_0

OLLAMA GGUF

qwen35 · 9.0B · Q8_0

Good

Jun 28, 2026 · Apple M4 Pro

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Good

Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K

Global Score
65 vs 77
Hardware Fit
96 vs 75
Quality Score
52 vs 78

Hardware

richardyoung/qwyth… qwen3.5:9b
MachineMac miniASUS
CPUApple M4 ProIntel Gen Intel® Core™ i7-13700K
Cores1224
RAM24 GB64 GB
GPUApple M4 ProNVIDIA GeForce RTX 3070
OSmacOS 15.6.1Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedunknown

Performance

richardyoung/qwyth… qwen3.5:9b
Tokens/sec25.330.5
First chunk397 ms291 ms
TTFT397 ms291 ms
Load time6.3 s4.8 s
Memory usage8.3 GB8.8 GB
Memory %34%14%

HW Fit Score Breakdown

richardyoung/qwythos-9b…

Speed
47/50
TTFT
20/20
Memory
29/30

qwen3.5:9b

Speed
34/50
TTFT
20/20
Memory
21/30

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

qwen3.5:9b

Reasoning
14/20
Coding
15/20
Instruction
14/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest