huihui_ai/Qwen3.8-abliterated:27b
OLLAMA GGUFqwen35 · 27.3B · Q4_K_M
Aug 25, 2026 · AMD RYZEN AI MAX+ 395
phi3:3.8b
OLLAMA GGUFphi3 · 3.8B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
80 vs 64
Hardware Fit
65 vs 100
Quality Score
87 vs 48
Hardware
huihui_ai/Qwen3.8-… phi3:3.8b
MachineAZW GTR ProMacBook Air
CPUAMD RYZEN AI MAX+ 395Apple M4
Cores3210
RAM125 GB32 GB
GPURadeon 8060SApple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archx64arm64
Power Modelow-powerbalanced
Performance
huihui_ai/Qwen3.8-… phi3:3.8b
Tokens/sec17.542.0
First chunk597 msN/A
TTFT597 ms142 ms
Load time7.1 s1.1 s
Memory usage17.4 GB16.0 GB
Memory %14%50%
HW Fit Score Breakdown
huihui_ai/Qwen3.8-ablit…
Speed
16/50
TTFT
19/20
Memory
30/30
phi3:3.8b
Speed
40/50
TTFT
30/20
Memory
30/30
Quality
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
phi3:3.8b
Reasoning
12/20
Coding
3/20
Instruction
11/20
Structured
10/15
Math
5/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Weak Multilingual: Adequate
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