Back to leaderboard

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Marginal

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

qwen3.6:35b-mlx

OLLAMA GGUF

nvfp4

Not Rec.

Jul 17, 2026 · Apple M5 Max

Global Score
57 vs 80
Hardware Fit
61 vs 77
Quality Score
55 vs 81

Hardware

qwen3.5:9b qwen3.6:35b-mlx
MachineAZW GTR ProMacBook Pro
CPUAMD RYZEN AI MAX+ 395Apple M5 Max
Cores3218
RAM125 GB48 GB
GPUAMD Radeon 8060SApple M5 Max
OSUbuntu 24.04.4 LTSmacOS 26.5.2
Archx64arm64
Power Modelow-powerbalanced

Performance

qwen3.5:9b qwen3.6:35b-mlx
Tokens/sec30.3129.8
First chunk205 ms77 ms
TTFT8.7 s30.0 s
Load time5.6 s1.8 s
Memory usage18.8 GB19.7 GB
Memory %15%41%

HW Fit Score Breakdown

qwen3.5:9b

Speed
30/50
TTFT
1/20
Memory
30/30

qwen3.6:35b-mlx

Speed
50/50
TTFT
0/20
Memory
27/30

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

qwen3.6:35b-mlx

Reasoning
19/20
Coding
9/20
Instruction
18/20
Structured
11/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Strong Structured Output: Adequate Math: Strong Multilingual: Strong
View qwen3.5:9b details | View qwen3.6:35b-mlx 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