Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

qwen3.8-27b-uncensored-hauhaucs-aggressive-mtp

LM-STUDIO GGUF

qwen35 · 27B

Good

Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor

Global Score
64 vs 78
Hardware Fit
69 vs 56
Quality Score
62 vs 87

Hardware

qwen3.5:4b qwen3.8-27b-uncens…
MachineLENOVO 20U30029MBSystem manufacturer
CPUIntel Core™ i5-10210UAMD Ryzen 7 5800X 8-Core Processor
Cores816
RAM15 GB31 GB
GPUCometLake-U GT2 [UHD Graphics]Navi 44 [Radeon RX 9060 XT]
OSPop 24.04 LTSUbuntu 26.04.1 LTS
Archx64x64
Power Modeperformanceperformance

Performance

qwen3.5:4b qwen3.8-27b-uncens…
Tokens/sec7.47.0
First chunk1815 ms19 ms
TTFT1.8 s1.2 s
Load time10.9 sN/A
Memory usage3.5 GB15.6 GB
Memory %23%50%

HW Fit Score Breakdown

qwen3.5:4b

Speed
19/50
TTFT
20/20
Memory
30/30

qwen3.8-27b-uncensored-…

Speed
11/50
TTFT
20/20
Memory
25/30

Quality

qwen3.5:4b

Reasoning
15/20
Coding
14/20
Instruction
6/20
Structured
12/15
Math
6/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Weak Multilingual: Strong

qwen3.8-27b-uncensored-…

Reasoning
17/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
11/15
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