Back to leaderboard

qwen3:4b

OLLAMA GGUF

qwen3 · 4.0B · Q4_K_M

Not Rec.

Nov 4, 2026 · Intel Core™ i7-9700

gemma-3-4b-it-q4-k-m

OLLAMA GGUF

llama · 4B · Q4_K_M

Excellent

Jul 9, 2026 · Intel Core™ i5-10400

Global Score
29 vs 80
Hardware Fit
84 vs 100
Quality Score
6 vs 71

Hardware

qwen3:4b gemma-3-4b-it-q4-k-m
MachineVMware, Inc. VMware Virtual PlatformMac Pro
CPUIntel Core™ i7-9700Intel Core™ i5-10400
Cores412
RAM16 GB32 GB
GPUIntegrated / UnknownAMD Radeon RX 6700 XT
OSUbuntu 24.04.5 LTSmacOS 26.5.1
Archx64x64
Power Modeunknownbalanced

Performance

qwen3:4b gemma-3-4b-it-q4-k-m
Tokens/sec10.475.0
First chunk857 ms136 ms
TTFT857 ms136 ms
Load time41.0 s0.0 s
Memory usage3.0 GB0.8 GB
Memory %19%3%

HW Fit Score Breakdown

qwen3:4b

Speed
34/50
TTFT
20/20
Memory
30/30

gemma-3-4b-it-q4-k-m

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

Quality

qwen3:4b

Reasoning
0/20
Coding
2/20
Instruction
2/20
Structured
0/15
Math
1/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

gemma-3-4b-it-q4-k-m

Reasoning
11/20
Coding
17/20
Instruction
14/20
Structured
14/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3:4b details | View gemma-3-4b-it-q4-k-m 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