Back to leaderboard

qwen3:4b

OLLAMA GGUF

qwen3 · 4.0B · Q4_K_M

Not Rec.

Nov 4, 2026 · Intel Core™ i7-9700

qwen/qwen3.5-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q6_K

Not Rec.

Sep 19, 2026 · AMD Ryzen 7 5800X 8-Core Processor

Global Score
29 vs 72
Hardware Fit
84 vs 35
Quality Score
6 vs 88

Hardware

qwen3:4b qwen/qwen3.5-35b-a3b
MachineVMware, Inc. VMware Virtual PlatformSystem manufacturer
CPUIntel Core™ i7-9700AMD Ryzen 7 5800X 8-Core Processor
Cores416
RAM16 GB32 GB
GPUIntegrated / UnknownAMD Radeon RX 9060 XT
OSUbuntu 24.04.5 LTSMicrosoft Windows 11 Home 10.0.26200
Archx64x64
Power Modeunknownbalanced

Performance

qwen3:4b qwen/qwen3.5-35b-a3b
Tokens/sec10.48.3
First chunk857 ms32 ms
TTFT857 ms2.0 s
Load time41.0 sN/A
Memory usage3.0 GB28.9 GB
Memory %19%91%

HW Fit Score Breakdown

qwen3:4b

Speed
34/50
TTFT
20/20
Memory
30/30

qwen/qwen3.5-35b-a3b

Speed
13/50
TTFT
17/20
Memory
5/30

Quality

qwen3:4b

Reasoning
0/20
Coding
2/20
Instruction
2/20
Structured
0/15
Math
1/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

qwen/qwen3.5-35b-a3b

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3:4b details | View qwen/qwen3.5-35b-a3b 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