Back to leaderboard

qwen3-coder:latest

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Good

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

qwen3.8-27b-uncensored-hauhaucs-aggressive-mtp

LM-STUDIO GGUF

qwen35 · 27B

Good

Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor

Global Score
76 vs 78
Hardware Fit
51 vs 56
Quality Score
87 vs 87

Hardware

qwen3-coder:latest qwen3.8-27b-uncens…
MachineDell Inc. Inspiron 15 3530System manufacturer
CPUIntel Gen Intel® Core™ i7-1355UAMD Ryzen 7 5800X 8-Core Processor
Cores1216
RAM31 GB31 GB
GPURaptor Lake-P [Iris Xe Graphics]Navi 44 [Radeon RX 9060 XT]
OScachyos rollingUbuntu 26.04.1 LTS
Archx64x64
Power Modelow-powerperformance

Performance

qwen3-coder:latest qwen3.8-27b-uncens…
Tokens/sec7.67.0
First chunk2037 ms19 ms
TTFT2.0 s1.2 s
Load time8.7 sN/A
Memory usage18.9 GB15.6 GB
Memory %61%50%

HW Fit Score Breakdown

qwen3-coder:latest

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

qwen3.8-27b-uncensored-…

Speed
11/50
TTFT
20/20
Memory
25/30

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

qwen3.8-27b-uncensored-…

Reasoning
17/20
Coding
19/20
Instruction
15/20
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-coder:latest details | View qwen3.8-27b-uncens… 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