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

phi4:14b

OLLAMA GGUF

phi3 · 14.7B · Q4_K_M

Good

Jun 26, 2026 · Cortex-X925

Global Score
67 vs 77
Hardware Fit
66 vs 74
Quality Score
67 vs 78

Hardware

parable-qwen3-4b-c… phi4:14b
MachineGigabyte Technology Co., Ltd. H310M S2 2.0NVIDIA NVIDIA_DGX_Spark
CPUIntel Core™ i3-9100FCortex-X925
Cores420
RAM16 GB122 GB
GPUVirtual Desktop Monitor, NVIDIA GeForce GTX 1650Device 2e12
OSМайкрософт Windows 10 Pro 10.0.19045Ubuntu 24.04.4 LTS
Archx64arm64
Power Modebalancedperformance

Performance

parable-qwen3-4b-c… phi4:14b
Tokens/sec4.322.9
First chunk13 ms198 ms
TTFT1.9 s198 ms
Load timeN/A10.3 s
Memory usage3.0 GB14.7 GB
Memory %19%12%

HW Fit Score Breakdown

parable-qwen3-4b-claude…

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

phi4:14b

Speed
24/50
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

phi4:14b

Reasoning
18/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View parable-qwen3-4b-c… details | View phi4:14b 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