gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Apr 13, 2026 · Apple M4 Max
huihui_ai/Qwen3.8-abliterated:27b
OLLAMA GGUFqwen35 · 27.3B · Q4_K_M
Aug 25, 2026 · AMD RYZEN AI MAX+ 395
Global Score
76 vs 80
Hardware Fit
46 vs 65
Quality Score
89 vs 87
Hardware
gemma4:31b huihui_ai/Qwen3.8-…
MachineMacBook ProAZW GTR Pro
CPUApple M4 MaxAMD RYZEN AI MAX+ 395
Cores1632
RAM64 GB125 GB
GPUApple M4 MaxRadeon 8060S
OSmacOS 26.3.1Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedlow-power
Performance
gemma4:31b huihui_ai/Qwen3.8-…
Tokens/sec22.417.5
First chunk565 ms597 ms
TTFT30.0 s597 ms
Load time6.9 s7.1 s
Memory usage43.9 GB17.4 GB
Memory %69%14%
HW Fit Score Breakdown
gemma4:31b
Speed
30/50
TTFT
0/20
Memory
16/30
huihui_ai/Qwen3.8-ablit…
Speed
16/50
TTFT
19/20
Memory
30/30
Quality
gemma4:31b
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
huihui_ai/Qwen3.8-ablit…
Reasoning
17/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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