Back to leaderboard

qwen3-coder:latest

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Good

May 24, 2026 · Intel Gen Intel® Core™ i7-1355U

qwen3.6-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · IQ3_XXS

Good

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

Global Score
76 vs 79
Hardware Fit
51 vs 59
Quality Score
87 vs 87

Hardware

qwen3-coder:latest qwen3.6-35b-a3b
MachineDell Inc. Inspiron 15 3530Docker Container
CPUIntel Gen Intel® Core™ i7-1355UIntel Gen Intel® Core™ i9-11900H
Cores1216
RAM31 GB15 GB
GPURaptor Lake-P [Iris Xe Graphics]TigerLake-H GT1 [UHD Graphics]
OScachyos rollingUbuntu 26.04 LTS
Archx64x64
Power Modelow-powerperformance

Performance

qwen3-coder:latest qwen3.6-35b-a3b
Tokens/sec7.69.3
First chunk2037 ms21 ms
TTFT2.0 s3.6 s
Load time8.7 s32.0 s
Memory usage18.9 GB1.8 GB
Memory %61%12%

HW Fit Score Breakdown

qwen3-coder:latest

Speed
13/50
TTFT
18/20
Memory
20/30

qwen3.6-35b-a3b

Speed
17/50
TTFT
12/20
Memory
30/30

Quality

qwen3-coder:latest

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

qwen3.6-35b-a3b

Reasoning
17/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3-coder:latest details | View qwen3.6-35b-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