Back to leaderboard

llama-3.1-8b-instruct

LM-STUDIO GGUF

llama · 8B · Q8_0

Excellent

Apr 26, 2026 · AMD Ryzen 5 5500

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
81 vs 88
Hardware Fit
100 vs 85
Quality Score
73 vs 89

Hardware

llama-3.1-8b-instr… huihui-qwen3.6-35b…
MachineASUSGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUAMD Ryzen 5 5500AMD Ryzen 5 5600X 6-Core Processor
Cores1212
RAM31 GB47 GB
GPUNavi 44 [Radeon RX 9060 XT]AD106 [GeForce RTX 4060 Ti]
OSNobara Linux 43cachyos rolling
Archx64x64
Power Modeperformancelow-power

Performance

llama-3.1-8b-instr… huihui-qwen3.6-35b…
Tokens/sec35.637.7
First chunk52 ms18 ms
TTFT256 ms2.9 s
Load timeN/AN/A
Memory usage8.6 GB26.1 GB
Memory %28%56%

HW Fit Score Breakdown

llama-3.1-8b-instruct

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

huihui-qwen3.6-35b-a3b-…

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

Quality

llama-3.1-8b-instruct

Reasoning
13/20
Coding
17/20
Instruction
13/20
Structured
15/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

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