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

qwen3.5-35b-a3b-uncensored-hauhaucs-aggressive

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K_M

Good

Apr 21, 2026 · Apple M2 Max

Global Score
67 vs 71
Hardware Fit
66 vs 92
Quality Score
67 vs 62

Hardware

parable-qwen3-4b-c… qwen3.5-35b-a3b-un…
MachineGigabyte Technology Co., Ltd. H310M S2 2.0Mac Studio
CPUIntel Core™ i3-9100FApple M2 Max
Cores412
RAM16 GB96 GB
GPUVirtual Desktop Monitor, NVIDIA GeForce GTX 1650Apple M2 Max
OSМайкрософт Windows 10 Pro 10.0.19045macOS 26.1
Archx64arm64
Power Modebalancedbalanced

Performance

parable-qwen3-4b-c… qwen3.5-35b-a3b-un…
Tokens/sec4.359.8
First chunk13 ms12 ms
TTFT1.9 s2.4 s
Load timeN/AN/A
Memory usage3.0 GB29.7 GB
Memory %19%31%

HW Fit Score Breakdown

parable-qwen3-4b-claude…

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

qwen3.5-35b-a3b-uncenso…

Speed
50/50
TTFT
12/20
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

qwen3.5-35b-a3b-uncenso…

Reasoning
18/20
Coding
8/20
Instruction
13/20
Structured
6/15
Math
12/15
Multilingual
5/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate Structured Output: Weak Math: Strong Multilingual: Adequate
View parable-qwen3-4b-c… details | View qwen3.5-35b-a3b-un… 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