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

qwen3.8-27b-claude-opus-reasoning-distilled

LM-STUDIO GGUF

qwen35 · 27B · Q4_K_M

Excellent

Aug 20, 2026 · Apple M4 Max

Global Score
80 vs 80
Hardware Fit
65 vs 63
Quality Score
87 vs 87

Hardware

huihui_ai/Qwen3.8-… qwen3.8-27b-claude…
MachineAZW GTR ProMacBook Pro
CPUAMD RYZEN AI MAX+ 395Apple M4 Max
Cores3216
RAM125 GB128 GB
GPURadeon 8060SApple M4 Max
OSUbuntu 24.04.4 LTSmacOS 26.5.2
Archx64arm64
Power Modelow-powerbalanced

Performance

huihui_ai/Qwen3.8-… qwen3.8-27b-claude…
Tokens/sec17.524.0
First chunk597 ms20 ms
TTFT597 ms4.5 s
Load time7.1 sN/A
Memory usage17.4 GB15.7 GB
Memory %14%12%

HW Fit Score Breakdown

huihui_ai/Qwen3.8-ablit…

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

qwen3.8-27b-claude-opus…

Speed
27/50
TTFT
6/20
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

qwen3.8-27b-claude-opus…

Reasoning
19/20
Coding
18/20
Instruction
11/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
View huihui_ai/Qwen3.8-… details | View qwen3.8-27b-claude… 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