Back to leaderboard

parable-qwen3-4b-claude-fable-5

LM-STUDIO GGUF

qwen3 · 4B · Q4_K_M

Good

Oct 24, 2026 · Intel Core™ i3-9100F

qwen2.5-coder:3b

OLLAMA GGUF

qwen2 · 3.1B · Q4_K_M

Good

Jun 26, 2026 · Cortex-A78AE

Global Score
67 vs 73
Hardware Fit
66 vs 100
Quality Score
67 vs 61

Hardware

parable-qwen3-4b-c… qwen2.5-coder:3b
MachineGigabyte Technology Co., Ltd. H310M S2 2.0NVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUIntel Core™ i3-9100FCortex-A78AE
Cores46
RAM16 GB7 GB
GPUVirtual Desktop Monitor, NVIDIA GeForce GTX 1650Integrated / Unknown
OSМайкрософт Windows 10 Pro 10.0.19045Ubuntu 22.04.5 LTS
Archx64arm64
Power Modebalancedbalanced

Performance

parable-qwen3-4b-c… qwen2.5-coder:3b
Tokens/sec4.321.3
First chunk13 ms969 ms
TTFT1.9 s969 ms
Load timeN/A6.6 s
Memory usage3.0 GB2.0 GB
Memory %19%27%

HW Fit Score Breakdown

parable-qwen3-4b-claude…

Speed
16/50
TTFT
20/20
Memory
30/30

qwen2.5-coder:3b

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

Quality

parable-qwen3-4b-claude…

Reasoning
12/20
Coding
12/20
Instruction
13/20
Structured
15/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

qwen2.5-coder:3b

Reasoning
8/20
Coding
15/20
Instruction
11/20
Structured
14/15
Math
4/15
Multilingual
9/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View parable-qwen3-4b-c… details | View qwen2.5-coder:3b 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