Back to leaderboard

qwen3.5-9b@q5_k_xl

LM-STUDIO GGUF

qwen35 · 9B · Q5_K_XL

Good

Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H

qwen3.5:35b-a3b

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Mar 6, 2026 · Apple M4 Pro

Global Score
73 vs 59
Hardware Fit
47 vs 69
Quality Score
84 vs 54

Hardware

qwen3.5-9b@q5_k_xl qwen3.5:35b-a3b
MachineDocker ContainerMacBook Pro
CPUIntel Gen Intel® Core™ i9-11900HApple M4 Pro
Cores1614
RAM15 GB48 GB
GPUTigerLake-H GT1 [UHD Graphics]Apple M4 Pro
OSUbuntu 26.04 LTSmacOS 26.3.1
Archx64arm64
Power Modeperformancebalanced

Performance

qwen3.5-9b@q5_k_xl qwen3.5:35b-a3b
Tokens/sec5.630.5
First chunk19 ms333 ms
TTFT5.6 s30.0 s
Load time12.5 s9.8 s
Memory usage0.0 GB25.1 GB
Memory %0%52%

HW Fit Score Breakdown

qwen3.5-9b@q5_k_xl

Speed
10/50
TTFT
7/20
Memory
30/30

qwen3.5:35b-a3b

Speed
45/50
TTFT
0/20
Memory
24/30

Quality

qwen3.5-9b@q5_k_xl

Reasoning
15/20
Coding
17/20
Instruction
17/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

qwen3.5:35b-a3b

Reasoning
18/20
Coding
1/20
Instruction
7/20
Structured
6/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Strong
View qwen3.5-9b@q5_k_xl details | View qwen3.5:35b-a3b 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