Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Mar 5, 2026 · Intel Core™ i5-6500

qwen3.8-27b-uncensored-ymq-mtp

LM-STUDIO GGUF

qwen35 · 27B

Excellent

Sep 12, 2026 · AMD Ryzen 5 5600X 6-Core Processor

Global Score
61 vs 84
Hardware Fit
69 vs 81
Quality Score
58 vs 85

Hardware

qwen3.5:4b qwen3.8-27b-uncens…
MachineGigabyte Technology Co., Ltd. H170M-D3HGigabyte Technology Co., Ltd. X570 AORUS PRO
CPUIntel Core™ i5-6500AMD Ryzen 5 5600X 6-Core Processor
Cores412
RAM16 GB32 GB
GPUGP104 [GeForce GTX 1070]NVIDIA GeForce RTX 5070 Ti
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modelow-powerbalanced

Performance

qwen3.5:4b qwen3.8-27b-uncens…
Tokens/sec35.718.3
First chunk438 ms9 ms
TTFT5.1 s522 ms
Load time40.1 s7.7 s
Memory usage5.5 GB14.9 GB
Memory %35%47%

HW Fit Score Breakdown

qwen3.5:4b

Speed
50/50
TTFT
11/20
Memory
8/30

qwen3.8-27b-uncensored-…

Speed
35/50
TTFT
20/20
Memory
26/30

Quality

qwen3.5:4b

Reasoning
18/20
Coding
1/20
Instruction
8/20
Structured
8/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Adequate Math: Strong Multilingual: Strong

qwen3.8-27b-uncensored-…

Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.5:4b details | View qwen3.8-27b-uncens… 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