Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

slim-rpcache-ornith-1.0-9b

LM-STUDIO GGUF

qwen35 · 9B · BF16

Good

Jul 4, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

Global Score
64 vs 79
Hardware Fit
69 vs 78
Quality Score
62 vs 79

Hardware

qwen3.5:4b slim-rpcache-ornit…
MachineLENOVO 20U30029MBASUS
CPUIntel Core™ i5-10210UAMD Ryzen 7 7800X3D 8-Core Processor
Cores816
RAM15 GB31 GB
GPUCometLake-U GT2 [UHD Graphics]NVIDIA GeForce RTX 4090, Raphael
OSPop 24.04 LTScachyos rolling
Archx64x64
Power Modeperformanceperformance

Performance

qwen3.5:4b slim-rpcache-ornit…
Tokens/sec7.452.3
First chunk1815 ms11 ms
TTFT1.8 s177 ms
Load time10.9 sN/A
Memory usage3.5 GB25.6 GB
Memory %23%84%

HW Fit Score Breakdown

qwen3.5:4b

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

slim-rpcache-ornith-1.0…

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

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

slim-rpcache-ornith-1.0…

Reasoning
16/20
Coding
16/20
Instruction
14/20
Structured
14/15
Math
9/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.5:4b details | View slim-rpcache-ornit… 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