Back to leaderboard

qwen3-5-4b-q4-k-m

OLLAMA GGUF

llama · 4B · Q4_K_M

Excellent

Jul 9, 2026 · Intel Core™ i5-10400

qwen3.6:35b-a3b

OLLAMA GGUF

qwen35moe · 35.5B · Q4_K_M

Excellent

Sep 15, 2026 · Intel Core™ i5-14400F

Global Score
83 vs 86
Hardware Fit
100 vs 87
Quality Score
76 vs 86

Hardware

qwen3-5-4b-q4-k-m qwen3.6:35b-a3b
MachineMac ProGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUIntel Core™ i5-10400Intel Core™ i5-14400F
Cores1216
RAM32 GB32 GB
GPUAMD Radeon RX 6700 XTNVIDIA GeForce RTX 5060 Ti
OSmacOS 26.5.1Microsoft Windows 11 Professionnel 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

qwen3-5-4b-q4-k-m qwen3.6:35b-a3b
Tokens/sec62.759.5
First chunk278 ms380 ms
TTFT278 ms380 ms
Load time0.0 s24.6 s
Memory usage0.0 GB20.9 GB
Memory %0%66%

HW Fit Score Breakdown

qwen3-5-4b-q4-k-m

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

qwen3.6:35b-a3b

Speed
50/50
TTFT
20/20
Memory
17/30

Quality

qwen3-5-4b-q4-k-m

Reasoning
14/20
Coding
15/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

qwen3.6:35b-a3b

Reasoning
16/20
Coding
17/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3-5-4b-q4-k-m details | View qwen3.6:35b-a3b 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