Back to leaderboard

qwen3.6:35b-a3b-q8_0

OLLAMA GGUF

qwen35moe · 36.0B · Q8_0

Excellent

Jul 7, 2026 · Cortex-X925

google/gemma-4-12b-qat

LM-STUDIO GGUF

gemma4 · 12B · Q4_0

Excellent

Aug 19, 2026 · AMD Ryzen 7 9700X 8-Core Processor

Global Score
91 vs 92
Hardware Fit
99 vs 100
Quality Score
87 vs 89

Hardware

qwen3.6:35b-a3b-q8_0 google/gemma-4-12b…
MachineASUSTeK COMPUTER INC. GX10Micro-Star International Co., Ltd. MS-7E51
CPUCortex-X925AMD Ryzen 7 9700X 8-Core Processor
Cores2016
RAM122 GB31 GB
GPUDevice 2e12NVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modeperformancebalanced

Performance

qwen3.6:35b-a3b-q8_0 google/gemma-4-12b…
Tokens/sec56.290.7
First chunk531 ms26 ms
TTFT531 ms127 ms
Load time32.8 sN/A
Memory usage41.0 GB6.7 GB
Memory %34%21%

HW Fit Score Breakdown

qwen3.6:35b-a3b-q8_0

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

google/gemma-4-12b-qat

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

Quality

qwen3.6:35b-a3b-q8_0

Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

google/gemma-4-12b-qat

Reasoning
17/20
Coding
19/20
Instruction
18/20
Structured
15/15
Math
11/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.6:35b-a3b-q8_0 details | View google/gemma-4-12b… 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