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

rnj-1:8b

OLLAMA GGUF

gemma3 · 8.3B · Q4_K_M

Excellent

Aug 24, 2026 · Apple M1 Pro

Global Score
67 vs 80
Hardware Fit
66 vs 93
Quality Score
67 vs 74

Hardware

parable-qwen3-4b-c… rnj-1:8b
MachineGigabyte Technology Co., Ltd. H310M S2 2.0MacBook Pro
CPUIntel Core™ i3-9100FApple M1 Pro
Cores410
RAM16 GB16 GB
GPUVirtual Desktop Monitor, NVIDIA GeForce GTX 1650Apple M1 Pro
OSМайкрософт Windows 10 Pro 10.0.19045macOS 26.6.2
Archx64arm64
Power Modebalancedbalanced

Performance

parable-qwen3-4b-c… rnj-1:8b
Tokens/sec4.322.3
First chunk13 ms404 ms
TTFT1.9 s404 ms
Load timeN/A3.7 s
Memory usage3.0 GB8.3 GB
Memory %19%52%

HW Fit Score Breakdown

parable-qwen3-4b-claude…

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

rnj-1:8b

Speed
49/50
TTFT
20/20
Memory
24/30

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

rnj-1:8b

Reasoning
12/20
Coding
19/20
Instruction
15/20
Structured
5/15
Math
14/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Weak Math: Strong Multilingual: Strong
View parable-qwen3-4b-c… details | View rnj-1:8b 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