Back to leaderboard

richardyoung/qwythos-9b-abliterated:Q8_0

OLLAMA GGUF

qwen35 · 9.0B · Q8_0

Good

Jun 28, 2026 · Apple M4 Pro

ministral-3:3b

OLLAMA GGUF

mistral3 · 3.8B · Q4_K_M

Good

Mar 6, 2026 · Apple M4

Global Score
65 vs 71
Hardware Fit
96 vs 99
Quality Score
52 vs 59

Hardware

richardyoung/qwyth… ministral-3:3b
MachineMac miniMacBook Air
CPUApple M4 ProApple M4
Cores1210
RAM24 GB32 GB
GPUApple M4 ProApple M4
OSmacOS 15.6.1macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

richardyoung/qwyth… ministral-3:3b
Tokens/sec25.342.2
First chunk397 ms189 ms
TTFT397 ms189 ms
Load time6.3 s1.2 s
Memory usage8.3 GB7.0 GB
Memory %34%22%

HW Fit Score Breakdown

richardyoung/qwythos-9b…

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

ministral-3:3b

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

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

ministral-3:3b

Reasoning
5/20
Coding
16/20
Instruction
11/20
Structured
14/15
Math
4/15
Multilingual
9/10
Reasoning: Weak Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak 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