Back to leaderboard

richardyoung/qwythos-9b-abliterated:Q8_0

OLLAMA GGUF

qwen35 · 9.0B · Q8_0

Good

Jun 28, 2026 · Apple M4 Pro

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Marginal

Mar 5, 2026 · Apple M4

Global Score
65 vs 48
Hardware Fit
96 vs 77
Quality Score
52 vs 35

Hardware

richardyoung/qwyth… qwen3.5:4b
MachineMac miniMac mini
CPUApple M4 ProApple M4
Cores1210
RAM24 GB16 GB
GPUApple M4 ProApple M4
OSmacOS 15.6.1macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

richardyoung/qwyth… qwen3.5:4b
Tokens/sec25.318.9
First chunk397 ms316 ms
TTFT397 ms13.0 s
Load time6.3 s3.7 s
Memory usage8.3 GB5.9 GB
Memory %34%37%

HW Fit Score Breakdown

richardyoung/qwythos-9b…

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

qwen3.5:4b

Speed
43/50
TTFT
4/20
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

qwen3.5:4b

Reasoning
10/20
Coding
1/20
Instruction
4/20
Structured
3/15
Math
8/15
Multilingual
9/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor 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