richardyoung/qwythos-9b-abliterated:Q8_0
OLLAMA GGUFqwen35 · 9.0B · Q8_0
Jun 28, 2026 · Apple M4 Pro
gptoss · 20.9B · MXFP4
OLLAMA GGUFgptoss · 20.9 · MXFP4
Jul 9, 2026 · Intel Core™ i5-10400
Global Score
65 vs 84
Hardware Fit
96 vs 69
Quality Score
52 vs 91
Hardware
richardyoung/qwyth… gptoss · 20.9B · M…
MachineMac miniMac Pro
CPUApple M4 ProIntel Core™ i5-10400
Cores1212
RAM24 GB32 GB
GPUApple M4 ProAMD Radeon RX 6700 XT
OSmacOS 15.6.1macOS 26.5.1
Archarm64x64
Power Modebalancedbalanced
Performance
richardyoung/qwyth… gptoss · 20.9B · M…
Tokens/sec25.317.5
First chunk397 ms643 ms
TTFT397 ms7.7 s
Load time6.3 s0.0 s
Memory usage8.3 GB0.8 GB
Memory %34%3%
HW Fit Score Breakdown
richardyoung/qwythos-9b…
Speed
47/50
TTFT
20/20
Memory
29/30
gptoss · 20.9B · MXFP4
Speed
34/50
TTFT
5/20
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
gptoss · 20.9B · MXFP4
Reasoning
19/20
Coding
19/20
Instruction
13/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest