Back to leaderboard

llama3.2:latest

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

May 27, 2026 · AMD Ryzen 5 2600X Six-Core Processor

Qwen3.8-27B-Ridge-3.7bpw_empero.ai:latest

OLLAMA GGUF

qwen35 · 27.3B · IQ2_M

Good

Aug 27, 2026 · AMD Ryzen 7 9700X 8-Core Processor

Global Score
76 vs 75
Hardware Fit
100 vs 99
Quality Score
65 vs 64

Hardware

llama3.2:latest Qwen3.8-27B-Ridge-…
MachineMicro-Star International Co., Ltd. MS-7B79Micro-Star International Co., Ltd. MS-7E51
CPUAMD Ryzen 5 2600X Six-Core ProcessorAMD Ryzen 7 9700X 8-Core Processor
Cores1216
RAM16 GB31 GB
GPUNVIDIA GeForce GTX 1080NVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSMicrosoft Windows 11 Famille 10.0.26200Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

llama3.2:latest Qwen3.8-27B-Ridge-…
Tokens/sec57.060.3
First chunk264 ms154 ms
TTFT264 ms154 ms
Load time9.7 s0.0 s
Memory usage2.6 GB11.0 GB
Memory %16%35%

HW Fit Score Breakdown

llama3.2:latest

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

Qwen3.8-27B-Ridge-3.7bp…

Speed
50/50
TTFT
20/20
Memory
29/30

Quality

llama3.2:latest

Reasoning
11/20
Coding
15/20
Instruction
15/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong

Qwen3.8-27B-Ridge-3.7bp…

Reasoning
20/20
Coding
17/20
Instruction
6/20
Structured
1/15
Math
14/15
Multilingual
6/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Poor Math: Strong 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