Back to leaderboard

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Excellent

Mar 7, 2026 · Intel Core™ i5-14600KF

qwen3.5-4b-mlx

LM-STUDIO MLX

qwen3_5 · 4B · 4bit

Not Rec.

Mar 6, 2026 · Apple M4 Pro

Global Score
84 vs 62
Hardware Fit
94 vs 35
Quality Score
80 vs 73

Hardware

qwen3.5:9b qwen3.5-4b-mlx
MachineASUSMac mini
CPUIntel Core™ i5-14600KFApple M4 Pro
Cores2014
RAM32 GB64 GB
GPUNVIDIA GeForce RTX 4070 Ti SUPERApple M4 Pro
OSMicrosoft Windows 11 Famille 10.0.26200macOS 15.7.4
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3.5:9b qwen3.5-4b-mlx
Tokens/sec86.30.0
First chunk316 ms5548 ms
TTFT316 ms5.5 s
Load time0.3 sN/A
Memory usage8.1 GB2.9 GB
Memory %25%5%

HW Fit Score Breakdown

qwen3.5:9b

Speed
50/50
TTFT
20/20
Memory
24/30

qwen3.5-4b-mlx

Speed
0/50
TTFT
6/20
Memory
29/30

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

qwen3.5-4b-mlx

Reasoning
17/20
Coding
17/20
Instruction
9/20
Structured
8/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Adequate Math: Strong Multilingual: Strong
View qwen3.5:9b details | View qwen3.5-4b-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