Back to leaderboard

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

OLLAMA GGUF

llama · 4B · Q4_K_M

Excellent

Jul 9, 2026 · Intel Core™ i5-10400

qwen2.5:1.5b

OLLAMA GGUF

qwen2 · 1.5B · Q4_K_M

Good

Jun 17, 2026 · ZHAOXIN KaiXian KX-7000 KaiXian KX-7000

Global Score
83 vs 65
Hardware Fit
100 vs 87
Quality Score
76 vs 56

Hardware

qwen3-5-4b-q4-k-m qwen2.5:1.5b
MachineMac ProShanghai Zhaoxin Semiconductor Co., Ltd. ZXE CRB
CPUIntel Core™ i5-10400ZHAOXIN KaiXian KX-7000 KaiXian KX-7000
Cores128
RAM32 GB30 GB
GPUAMD Radeon RX 6700 XTZX C-1190
OSmacOS 26.5.1Microsoft Windows 11 Pro 10.0.26100
Archx64x64
Power Modebalancedbalanced

Performance

qwen3-5-4b-q4-k-m qwen2.5:1.5b
Tokens/sec62.716.8
First chunk278 ms941 ms
TTFT278 ms941 ms
Load time0.0 s0.2 s
Memory usage0.0 GB1.0 GB
Memory %0%3%

HW Fit Score Breakdown

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

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

qwen2.5:1.5b

Speed
37/50
TTFT
20/20
Memory
30/30

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

qwen2.5:1.5b

Reasoning
8/20
Coding
10/20
Instruction
12/20
Structured
13/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3-5-4b-q4-k-m details | View qwen2.5:1.5b 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