Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Mar 5, 2026 · Intel Core™ i5-6500

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

OLLAMA GGUF

llama · 4B · Q4_K_M

Excellent

Jul 9, 2026 · Intel Core™ i5-10400

Global Score
61 vs 80
Hardware Fit
69 vs 100
Quality Score
58 vs 71

Hardware

qwen3.5:4b gemma-3-4b-it-q4-k-m
MachineGigabyte Technology Co., Ltd. H170M-D3HMac Pro
CPUIntel Core™ i5-6500Intel Core™ i5-10400
Cores412
RAM16 GB32 GB
GPUGP104 [GeForce GTX 1070]AMD Radeon RX 6700 XT
OSUbuntu 24.04.4 LTSmacOS 26.5.1
Archx64x64
Power Modelow-powerbalanced

Performance

qwen3.5:4b gemma-3-4b-it-q4-k-m
Tokens/sec35.775.0
First chunk438 ms136 ms
TTFT5.1 s136 ms
Load time40.1 s0.0 s
Memory usage5.5 GB0.8 GB
Memory %35%3%

HW Fit Score Breakdown

qwen3.5:4b

Speed
50/50
TTFT
11/20
Memory
8/30

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

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

Quality

qwen3.5:4b

Reasoning
18/20
Coding
1/20
Instruction
8/20
Structured
8/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Adequate Math: Strong Multilingual: Strong

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 qwen3.5:4b 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