Back to leaderboard

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Marginal

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

qwen3.5-35b-a3b-mtp

LM-STUDIO GGUF

qwen35moe · 35B · IQ3_XXS

Good

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

Global Score
57 vs 77
Hardware Fit
61 vs 51
Quality Score
55 vs 88

Hardware

qwen3.5:9b qwen3.5-35b-a3b-mtp
MachineAZW GTR ProDocker Container
CPUAMD RYZEN AI MAX+ 395Intel Gen Intel® Core™ i9-11900H
Cores3216
RAM125 GB15 GB
GPUAMD Radeon 8060STigerLake-H GT1 [UHD Graphics]
OSUbuntu 24.04.4 LTSUbuntu 26.04 LTS
Archx64x64
Power Modelow-powerperformance

Performance

qwen3.5:9b qwen3.5-35b-a3b-mtp
Tokens/sec30.37.8
First chunk205 ms30 ms
TTFT8.7 s5.6 s
Load time5.6 s32.5 s
Memory usage18.8 GB0.0 GB
Memory %15%0%

HW Fit Score Breakdown

qwen3.5:9b

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

qwen3.5-35b-a3b-mtp

Speed
14/50
TTFT
7/20
Memory
30/30

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

qwen3.5-35b-a3b-mtp

Reasoning
17/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.5:9b details | View qwen3.5-35b-a3b-mtp 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