qwen3.5:latest
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 8, 2026 · Apple M4
mlx-community/gemma-3-1b-it-8bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
Global Score
34 vs 72
Hardware Fit
58 vs 99
Quality Score
23 vs 61
Hardware
qwen3.5:latest mlx-community/gemm…
MachineMac miniMacBook Air
CPUApple M4Apple M4
Cores1010
RAM16 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5:latest mlx-community/gemm…
Tokens/sec13.386.3
First chunk438 ms253 ms
TTFT19.8 s253 ms
Load time0.2 sN/A
Memory usage8.0 GB1.1 GB
Memory %50%4%
HW Fit Score Breakdown
qwen3.5:latest
Speed
32/50
TTFT
1/20
Memory
25/30
mlx-community/gemma-3-1…
Speed
50/50
TTFT
20/20
Memory
29/30
Quality
qwen3.5:latest
Reasoning
6/20
Coding
1/20
Instruction
3/20
Structured
0/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Weak Multilingual: Strong
mlx-community/gemma-3-1…
Reasoning
7/20
Coding
14/20
Instruction
16/20
Structured
14/15
Math
2/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor 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