qwen3.5:9b
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 5, 2026 · AMD RYZEN AI MAX+ 395
mlx-community/gemma-3-1b-it-8bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
Global Score
57 vs 72
Hardware Fit
61 vs 99
Quality Score
55 vs 61
Hardware
qwen3.5:9b mlx-community/gemm…
MachineAZW GTR ProMacBook Air
CPUAMD RYZEN AI MAX+ 395Apple M4
Cores3210
RAM125 GB32 GB
GPUAMD Radeon 8060SApple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archx64arm64
Power Modelow-powerbalanced
Performance
qwen3.5:9b mlx-community/gemm…
Tokens/sec30.386.3
First chunk205 ms253 ms
TTFT8.7 s253 ms
Load time5.6 sN/A
Memory usage18.8 GB1.1 GB
Memory %15%4%
HW Fit Score Breakdown
qwen3.5:9b
Speed
30/50
TTFT
1/20
Memory
30/30
mlx-community/gemma-3-1…
Speed
50/50
TTFT
20/20
Memory
29/30
Quality
qwen3.5:9b
Reasoning
17/20
Coding
2/20
Instruction
7/20
Structured
8/15
Math
12/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Adequate Math: Strong 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