Back to leaderboard

richardyoung/qwythos-9b-abliterated:Q8_0

OLLAMA GGUF

qwen35 · 9.0B · Q8_0

Good

Jun 28, 2026 · Apple M4 Pro

qwen3-vl:30b

OLLAMA GGUF

qwen3vlmoe · 31.1B · Q4_K_M

Excellent

Mar 5, 2026 · Intel Core™ Ultra 9 285K

Global Score
65 vs 80
Hardware Fit
96 vs 98
Quality Score
52 vs 72

Hardware

richardyoung/qwyth… qwen3-vl:30b
MachineMac miniASUS
CPUApple M4 ProIntel Core™ Ultra 9 285K
Cores1224
RAM24 GB47 GB
GPUApple M4 ProNVIDIA GeForce RTX 5090, Intel(R) Graphics
OSmacOS 15.6.1Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

richardyoung/qwyth… qwen3-vl:30b
Tokens/sec25.3208.9
First chunk397 ms102 ms
TTFT397 ms684 ms
Load time6.3 s0.1 s
Memory usage8.3 GB22.0 GB
Memory %34%47%

HW Fit Score Breakdown

richardyoung/qwythos-9b…

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

qwen3-vl:30b

Speed
50/50
TTFT
20/20
Memory
28/30

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-vl:30b

Reasoning
14/20
Coding
6/20
Instruction
17/20
Structured
12/15
Math
13/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak Instruction Following: Strong Structured Output: Strong Math: Strong 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