Back to leaderboard

llama3.2:1b

OLLAMA GGUF

llama · 1.2B · Q8_0

Good

Jun 26, 2026 · Cortex-A78AE

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

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K

Excellent

Jun 13, 2026 · AMD Ryzen 5 5600X 6-Core Processor

Global Score
63 vs 88
Hardware Fit
100 vs 85
Quality Score
47 vs 89

Hardware

llama3.2:1b huihui-qwen3.6-35b…
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUCortex-A78AEAMD Ryzen 5 5600X 6-Core Processor
Cores612
RAM7 GB47 GB
GPUIntegrated / UnknownAD106 [GeForce RTX 4060 Ti]
OSUbuntu 22.04.5 LTScachyos rolling
Archarm64x64
Power Modebalancedlow-power

Performance

llama3.2:1b huihui-qwen3.6-35b…
Tokens/sec40.237.7
First chunk1087 ms18 ms
TTFT1.1 s2.9 s
Load time6.2 sN/A
Memory usage1.4 GB26.1 GB
Memory %19%56%

HW Fit Score Breakdown

llama3.2:1b

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

huihui-qwen3.6-35b-a3b-…

Speed
50/50
TTFT
13/20
Memory
22/30

Quality

llama3.2:1b

Reasoning
4/20
Coding
9/20
Instruction
14/20
Structured
13/15
Math
1/15
Multilingual
6/10
Reasoning: Poor Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate

huihui-qwen3.6-35b-a3b-…

Reasoning
19/20
Coding
15/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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