Back to leaderboard

qwen3.8:latest

OLLAMA GGUF

qwen35 · 27.3B · Q4_K_M

Good

Oct 2, 2026 · AMD Ryzen 9 5950X 16-Core Processor

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

Global Score
68 vs 64
Hardware Fit
22 vs 69
Quality Score
88 vs 62

Hardware

qwen3.8:latest qwen3.5:4b
MachineSystem manufacturerLENOVO 20U30029MB
CPUAMD Ryzen 9 5950X 16-Core ProcessorIntel Core™ i5-10210U
Cores328
RAM32 GB15 GB
GPUNVIDIA GeForce RTX 3090CometLake-U GT2 [UHD Graphics]
OSMicrosoft Windows 11 Pro 10.0.26300Pop 24.04 LTS
Archx64x64
Power Modebalancedperformance

Performance

qwen3.8:latest qwen3.5:4b
Tokens/sec10.07.4
First chunk1041 ms1815 ms
TTFT14.3 s1.8 s
Load time22.3 s10.9 s
Memory usage26.2 GB3.5 GB
Memory %82%23%

HW Fit Score Breakdown

qwen3.8:latest

Speed
12/50
TTFT
1/20
Memory
9/30

qwen3.5:4b

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

Quality

qwen3.8:latest

Reasoning
19/20
Coding
19/20
Instruction
10/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

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

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