Back to leaderboard

huihui_ai/Qwen3.8-abliterated:27b

OLLAMA GGUF

qwen35 · 27.3B · Q4_K_M

Excellent

Aug 25, 2026 · AMD RYZEN AI MAX+ 395

gpt-oss-safeguard-20b-mlx

LM-STUDIO MLX

gpt_oss · 20B · MXFP4

Excellent

Mar 12, 2026 · Apple M4

Global Score
80 vs 87
Hardware Fit
65 vs 82
Quality Score
87 vs 89

Hardware

huihui_ai/Qwen3.8-… gpt-oss-safeguard-…
MachineAZW GTR ProMac mini
CPUAMD RYZEN AI MAX+ 395Apple M4
Cores3210
RAM125 GB24 GB
GPURadeon 8060SApple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archx64arm64
Power Modelow-powerbalanced

Performance

huihui_ai/Qwen3.8-… gpt-oss-safeguard-…
Tokens/sec17.541.4
First chunk597 ms8 ms
TTFT597 ms3.6 s
Load time7.1 sN/A
Memory usage17.4 GB14.5 GB
Memory %14%61%

HW Fit Score Breakdown

huihui_ai/Qwen3.8-ablit…

Speed
16/50
TTFT
19/20
Memory
30/30

gpt-oss-safeguard-20b-mlx

Speed
50/50
TTFT
12/20
Memory
20/30

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

gpt-oss-safeguard-20b-mlx

Reasoning
19/20
Coding
12/20
Instruction
19/20
Structured
15/15
Math
15/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View huihui_ai/Qwen3.8-… details | View gpt-oss-safeguard-… details

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