gemma4:latest
OLLAMA GGUFgemma4 · 8.0B · Q4_K_M
Jul 11, 2026 · AMD Ryzen 9 9950X 16-Core Processor
richardyoung/qwythos-9b-abliterated:Q8_0
OLLAMA GGUFqwen35 · 9.0B · Q8_0
Jun 28, 2026 · Apple M4 Pro
Global Score
87 vs 65
Hardware Fit
75 vs 96
Quality Score
92 vs 52
Hardware
gemma4:latest richardyoung/qwyth…
MachineMicro-Star International Co., Ltd. MS-7E47Mac mini
CPUAMD Ryzen 9 9950X 16-Core ProcessorApple M4 Pro
Cores3212
RAM125 GB24 GB
GPUAMD Radeon(TM) Graphics, NVIDIA GeForce RTX 4080 SUPERApple M4 Pro
OSMicrosoft Windows 11 Pro 10.0.26100macOS 15.6.1
Archx64arm64
Power Modebalancedbalanced
Performance
gemma4:latest richardyoung/qwyth…
Tokens/sec42.425.3
First chunk472 ms397 ms
TTFT3.8 s397 ms
Load time0.3 s6.3 s
Memory usage12.3 GB8.3 GB
Memory %10%34%
HW Fit Score Breakdown
gemma4:latest
Speed
40/50
TTFT
5/20
Memory
30/30
richardyoung/qwythos-9b…
Speed
47/50
TTFT
20/20
Memory
29/30
Quality
gemma4:latest
Reasoning
19/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest