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

hf.co/unsloth/gemma-4-E4B-it-GGUF:Q5_K_M

OLLAMA GGUF

gemma4 · 7.52B · unknown

Excellent

Aug 23, 2026 · Apple M1 Pro

Global Score
80 vs 88
Hardware Fit
65 vs 100
Quality Score
87 vs 83

Hardware

huihui_ai/Qwen3.8-… hf.co/unsloth/gemm…
MachineAZW GTR ProMacBook Pro
CPUAMD RYZEN AI MAX+ 395Apple M1 Pro
Cores3210
RAM125 GB16 GB
GPURadeon 8060SApple M1 Pro
OSUbuntu 24.04.4 LTSmacOS 26.6.2
Archx64arm64
Power Modelow-powerbalanced

Performance

huihui_ai/Qwen3.8-… hf.co/unsloth/gemm…
Tokens/sec17.528.3
First chunk597 ms224 ms
TTFT597 ms224 ms
Load time7.1 s4.5 s
Memory usage17.4 GB3.6 GB
Memory %14%23%

HW Fit Score Breakdown

huihui_ai/Qwen3.8-ablit…

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

hf.co/unsloth/gemma-4-E…

Speed
50/50
TTFT
20/20
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

hf.co/unsloth/gemma-4-E…

Reasoning
14/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View huihui_ai/Qwen3.8-… details | View hf.co/unsloth/gemm… 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