Back to leaderboard

llama3.1:8b

OLLAMA GGUF

llama · 8.0B · Q4_K_M

Excellent

Sep 15, 2026 · Intel Core™ i5-14400F

unsloth/qwen3.6-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q3_K_M

Excellent

Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor

Global Score
81 vs 85
Hardware Fit
100 vs 79
Quality Score
73 vs 88

Hardware

llama3.1:8b unsloth/qwen3.6-35…
MachineGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4System manufacturer
CPUIntel Core™ i5-14400FAMD Ryzen 7 5800X 8-Core Processor
Cores1616
RAM32 GB31 GB
GPUNVIDIA GeForce RTX 5060 TiNavi 44 [Radeon RX 9060 XT]
OSMicrosoft Windows 11 Professionnel 10.0.26200Ubuntu 26.04.1 LTS
Archx64x64
Power Modebalancedperformance

Performance

llama3.1:8b unsloth/qwen3.6-35…
Tokens/sec70.223.5
First chunk58 ms54 ms
TTFT58 ms457 ms
Load time4.1 sN/A
Memory usage4.9 GB18.3 GB
Memory %15%59%

HW Fit Score Breakdown

llama3.1:8b

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

unsloth/qwen3.6-35b-a3b

Speed
38/50
TTFT
20/20
Memory
21/30

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

unsloth/qwen3.6-35b-a3b

Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View llama3.1:8b details | View unsloth/qwen3.6-35… details

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