Back to leaderboard

qwen3:8b

OLLAMA GGUF

qwen3 · 8.2B · Q4_K_M

Excellent

Mar 7, 2026 · Intel Core™ i5-14600KF

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
81 vs 88
Hardware Fit
96 vs 94
Quality Score
75 vs 85

Hardware

qwen3:8b huihui-qwen3.6-35b…
MachineASUSGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUIntel Core™ i5-14600KFAMD Ryzen 5 5600X 6-Core Processor
Cores2012
RAM32 GB47 GB
GPUNVIDIA GeForce RTX 4070 Ti SUPERAD106 [GeForce RTX 4060 Ti]
OSMicrosoft Windows 11 Famille 10.0.26200cachyos rolling
Archx64x64
Power Modebalancedlow-power

Performance

qwen3:8b huihui-qwen3.6-35b…
Tokens/sec109.139.8
First chunk190 ms3 ms
TTFT190 ms479 ms
Load time4.3 sN/A
Memory usage5.6 GB24.4 GB
Memory %18%52%

HW Fit Score Breakdown

qwen3:8b

Speed
50/50
TTFT
20/20
Memory
26/30

huihui-qwen3.6-35b-a3b-…

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

Quality

qwen3:8b

Reasoning
15/20
Coding
16/20
Instruction
14/20
Structured
14/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak 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