qwen3.6:35b-a3b-q8_0
OLLAMA GGUFqwen35moe · 36.0B · Q8_0
Jul 7, 2026 · Cortex-X925
mlx-community/gemma-3-4b-it-qat-4bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
Global Score
91 vs 80
Hardware Fit
99 vs 100
Quality Score
87 vs 71
Hardware
qwen3.6:35b-a3b-q8_0 mlx-community/gemm…
MachineASUSTeK COMPUTER INC. GX10MacBook Air
CPUCortex-X925Apple M4
Cores2010
RAM122 GB32 GB
GPUDevice 2e12Apple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archarm64arm64
Power Modeperformancebalanced
Performance
qwen3.6:35b-a3b-q8_0 mlx-community/gemm…
Tokens/sec56.243.2
First chunk531 ms428 ms
TTFT531 ms428 ms
Load time32.8 sN/A
Memory usage41.0 GB1.3 GB
Memory %34%4%
HW Fit Score Breakdown
qwen3.6:35b-a3b-q8_0
Speed
50/50
TTFT
20/20
Memory
29/30
mlx-community/gemma-3-4…
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
mlx-community/gemma-3-4…
Reasoning
9/20
Coding
17/20
Instruction
17/20
Structured
13/15
Math
5/15
Multilingual
10/10
Reasoning: Weak Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest