qwen3.5:9b
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 7, 2026 · Intel Core™ i5-14600KF
qwen3.6:35b-mlx
OLLAMA GGUFnvfp4
Jul 17, 2026 · Apple M5 Max
Global Score
85 vs 89
Hardware Fit
96 vs 97
Quality Score
80 vs 86
Hardware
qwen3.5:9b qwen3.6:35b-mlx
MachineASUSMacBook Pro
CPUIntel Core™ i5-14600KFApple M5 Max
Cores2018
RAM32 GB48 GB
GPUNVIDIA GeForce RTX 4070 Ti SUPERApple M5 Max
OSMicrosoft Windows 11 Famille 10.0.26200macOS 26.5.2
Archx64arm64
Power Modebalancedbalanced
Performance
qwen3.5:9b qwen3.6:35b-mlx
Tokens/sec88.6129.4
First chunk306 ms49 ms
TTFT306 ms49 ms
Load time7.0 s0.0 s
Memory usage8.1 GB20.5 GB
Memory %25%43%
HW Fit Score Breakdown
qwen3.5:9b
Speed
50/50
TTFT
20/20
Memory
26/30
qwen3.6:35b-mlx
Speed
50/50
TTFT
20/20
Memory
27/30
Quality
qwen3.5:9b
Reasoning
14/20
Coding
16/20
Instruction
15/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
qwen3.6:35b-mlx
Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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