Back to leaderboard

llama3.1:8b

OLLAMA GGUF

llama · 8.0B · Q4_K_M

Excellent

Sep 15, 2026 · Intel Core™ i5-14400F

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

llama3.1:8b huihui-qwen3.6-35b…
MachineGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4Gigabyte Technology Co., Ltd. B550M AORUS PRO
CPUIntel Core™ i5-14400FAMD Ryzen 5 5600X 6-Core Processor
Cores1612
RAM32 GB47 GB
GPUNVIDIA GeForce RTX 5060 TiAD106 [GeForce RTX 4060 Ti]
OSMicrosoft Windows 11 Professionnel 10.0.26200cachyos rolling
Archx64x64
Power Modebalancedlow-power

Performance

llama3.1:8b huihui-qwen3.6-35b…
Tokens/sec70.237.7
First chunk58 ms18 ms
TTFT58 ms2.9 s
Load time4.1 sN/A
Memory usage4.9 GB26.1 GB
Memory %15%56%

HW Fit Score Breakdown

llama3.1:8b

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

huihui-qwen3.6-35b-a3b-…

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

Quality

llama3.1:8b

Reasoning
12/20
Coding
18/20
Instruction
15/20
Structured
13/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong 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