Back to leaderboard

qwen3:8b

OLLAMA GGUF

qwen3 · 8.2B · Q4_K_M

Good

Aug 15, 2026 · AMD Ryzen 9 3900X 12-Core Processor

richardyoung/qwythos-9b-abliterated:Q8_0

OLLAMA GGUF

qwen35 · 9.0B · Q8_0

Good

Jun 28, 2026 · Apple M4 Pro

Global Score
78 vs 65
Hardware Fit
86 vs 96
Quality Score
74 vs 52

Hardware

qwen3:8b richardyoung/qwyth…
MachineMac mini
CPUAMD Ryzen 9 3900X 12-Core ProcessorApple M4 Pro
Cores2412
RAM64 GB24 GB
GPUNVIDIA GeForce RTX 4060 TiApple M4 Pro
OSMicrosoft Windows 11 Pro 10.0.26200macOS 15.6.1
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3:8b richardyoung/qwyth…
Tokens/sec48.525.3
First chunk202 ms397 ms
TTFT4.3 s397 ms
Load time4.2 s6.3 s
Memory usage5.5 GB8.3 GB
Memory %9%34%

HW Fit Score Breakdown

qwen3:8b

Speed
50/50
TTFT
6/20
Memory
30/30

richardyoung/qwythos-9b…

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

Quality

qwen3:8b

Reasoning
16/20
Coding
8/20
Instruction
14/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

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

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