Back to leaderboard

Qwen3.8-27B-Ridge-3.7bpw_empero.ai:latest

OLLAMA GGUF

qwen35 · 27.3B · IQ2_M

Good

Aug 27, 2026 · AMD Ryzen 7 9700X 8-Core Processor

unsloth/gemma-4-26b-a4b-it

LM-STUDIO GGUF

gemma4 · 26B · Q3_K_M

Excellent

Apr 5, 2026 · Apple M4

Global Score
75 vs 84
Hardware Fit
99 vs 64
Quality Score
64 vs 92

Hardware

Qwen3.8-27B-Ridge-… unsloth/gemma-4-26…
MachineMicro-Star International Co., Ltd. MS-7E51Mac mini
CPUAMD Ryzen 7 9700X 8-Core ProcessorApple M4
Cores1610
RAM31 GB24 GB
GPUNVIDIA GeForce RTX 5080, AMD Radeon(TM) GraphicsApple M4
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.3
Archx64arm64
Power Modebalancedbalanced

Performance

Qwen3.8-27B-Ridge-… unsloth/gemma-4-26…
Tokens/sec60.316.5
First chunk154 ms32 ms
TTFT154 ms2.2 s
Load time0.0 sN/A
Memory usage11.0 GB19.3 GB
Memory %35%80%

HW Fit Score Breakdown

Qwen3.8-27B-Ridge-3.7bp…

Speed
50/50
TTFT
20/20
Memory
29/30

unsloth/gemma-4-26b-a4b…

Speed
36/50
TTFT
18/20
Memory
10/30

Quality

Qwen3.8-27B-Ridge-3.7bp…

Reasoning
20/20
Coding
17/20
Instruction
6/20
Structured
1/15
Math
14/15
Multilingual
6/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Adequate

unsloth/gemma-4-26b-a4b…

Reasoning
18/20
Coding
19/20
Instruction
17/20
Structured
14/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

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