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

dolphin3:8b

OLLAMA GGUF

llama · 8.0B · Q4_K_M

Good

Mar 6, 2026 · Apple M4

Global Score
67 vs 74
Hardware Fit
66 vs 92
Quality Score
67 vs 66

Hardware

parable-qwen3-4b-c… dolphin3:8b
MachineGigabyte Technology Co., Ltd. H310M S2 2.0MacBook Air
CPUIntel Core™ i3-9100FApple M4
Cores410
RAM16 GB32 GB
GPUVirtual Desktop Monitor, NVIDIA GeForce GTX 1650Apple M4
OSМайкрософт Windows 10 Pro 10.0.19045macOS 26.3
Archx64arm64
Power Modebalancedbalanced

Performance

parable-qwen3-4b-c… dolphin3:8b
Tokens/sec4.321.0
First chunk13 ms314 ms
TTFT1.9 s314 ms
Load timeN/A0.8 s
Memory usage3.0 GB10.4 GB
Memory %19%33%

HW Fit Score Breakdown

parable-qwen3-4b-claude…

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

dolphin3:8b

Speed
42/50
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

dolphin3:8b

Reasoning
12/20
Coding
13/20
Instruction
13/20
Structured
14/15
Math
4/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View parable-qwen3-4b-c… details | View dolphin3:8b 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