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

huihui-qwen3.6-35b-a3b-claude-4.7-opus-abliterated-mtp

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K

Excellent

Jun 12, 2026 · AMD Ryzen 5 5600X 6-Core Processor

Global Score
76 vs 88
Hardware Fit
100 vs 94
Quality Score
65 vs 85

Hardware

llama3.2:latest huihui-qwen3.6-35b…
MachineMicro-Star International Co., Ltd. MS-7B79Gigabyte Technology Co., Ltd. B550M AORUS PRO
CPUAMD Ryzen 5 2600X Six-Core ProcessorAMD Ryzen 5 5600X 6-Core Processor
Cores1212
RAM16 GB47 GB
GPUNVIDIA GeForce GTX 1080AD106 [GeForce RTX 4060 Ti]
OSMicrosoft Windows 11 Famille 10.0.26200cachyos rolling
Archx64x64
Power Modebalancedlow-power

Performance

llama3.2:latest huihui-qwen3.6-35b…
Tokens/sec57.039.8
First chunk264 ms3 ms
TTFT264 ms479 ms
Load time9.7 sN/A
Memory usage2.6 GB24.4 GB
Memory %16%52%

HW Fit Score Breakdown

llama3.2:latest

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

huihui-qwen3.6-35b-a3b-…

Speed
50/50
TTFT
20/20
Memory
24/30

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

huihui-qwen3.6-35b-a3b-…

Reasoning
18/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

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