Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Mar 5, 2026 · Intel Core™ i5-6500

Qwen3.6-35B-A3B-Q4_K_M:latest

OLLAMA GGUF

qwen35moe · 34.7B · Q4_K_M

Excellent

Aug 18, 2026 · AMD Ryzen 7 9700X 8-Core Processor

Global Score
61 vs 86
Hardware Fit
69 vs 87
Quality Score
58 vs 86

Hardware

qwen3.5:4b Qwen3.6-35B-A3B-Q4…
MachineGigabyte Technology Co., Ltd. H170M-D3HMicro-Star International Co., Ltd. MS-7E51
CPUIntel Core™ i5-6500AMD Ryzen 7 9700X 8-Core Processor
Cores416
RAM16 GB31 GB
GPUGP104 [GeForce GTX 1070]NVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modelow-powerbalanced

Performance

qwen3.5:4b Qwen3.6-35B-A3B-Q4…
Tokens/sec35.792.9
First chunk438 ms362 ms
TTFT5.1 s362 ms
Load time40.1 s12.3 s
Memory usage5.5 GB20.7 GB
Memory %35%67%

HW Fit Score Breakdown

qwen3.5:4b

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

Qwen3.6-35B-A3B-Q4_K_M:…

Speed
50/50
TTFT
20/20
Memory
17/30

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

Qwen3.6-35B-A3B-Q4_K_M:…

Reasoning
16/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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