Back to leaderboard

Qwen3.8-27B-Opus-Distill-IQ3_XXS:latest

OLLAMA GGUF

qwen35 · 27.3B · IQ3_XXS

Good

Aug 19, 2026 · AMD Ryzen 7 9700X 8-Core Processor

qwen3:0.6b

OLLAMA GGUF

qwen3 · 751.63M · Q4_K_M

Good

Apr 29, 2026 · Intel Core™ i5-8350U

Global Score
73 vs 61
Hardware Fit
98 vs 85
Quality Score
62 vs 51

Hardware

Qwen3.8-27B-Opus-D… qwen3:0.6b
MachineMicro-Star International Co., Ltd. MS-7E51LENOVO 20L7CTO1WW
CPUAMD Ryzen 7 9700X 8-Core ProcessorIntel Core™ i5-8350U
Cores168
RAM31 GB23 GB
GPUNVIDIA GeForce RTX 5080, AMD Radeon(TM) GraphicsKaby Lake-R GT2 [UHD Graphics 620]
OSMicrosoft Windows 11 Pro 10.0.26200Fedora Linux 43
Archx64x64
Power Modebalancedlow-power

Performance

Qwen3.8-27B-Opus-D… qwen3:0.6b
Tokens/sec61.427.0
First chunk381 ms597 ms
TTFT381 ms8.7 s
Load time0.2 s1.8 s
Memory usage12.2 GB0.9 GB
Memory %39%4%

HW Fit Score Breakdown

Qwen3.8-27B-Opus-Distil…

Speed
50/50
TTFT
20/20
Memory
28/30

qwen3:0.6b

Speed
50/50
TTFT
5/20
Memory
30/30

Quality

Qwen3.8-27B-Opus-Distil…

Reasoning
17/20
Coding
18/20
Instruction
8/20
Structured
0/15
Math
13/15
Multilingual
6/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Adequate

qwen3:0.6b

Reasoning
14/20
Coding
0/20
Instruction
9/20
Structured
12/15
Math
9/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Strong Math: Adequate Multilingual: Adequate

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