Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

vicuna:13b

OLLAMA GGUF

llama · 13B · Q4_0

Marginal

Mar 1, 2026 · Apple M4

Global Score
64 vs 59
Hardware Fit
69 vs 84
Quality Score
62 vs 48

Hardware

qwen3.5:4b vicuna:13b
MachineLENOVO 20U30029MBMacBook Air
CPUIntel Core™ i5-10210UApple M4
Cores810
RAM15 GB32 GB
GPUCometLake-U GT2 [UHD Graphics]Apple M4
OSPop 24.04 LTSmacOS 26.3
Archx64arm64
Power Modeperformancebalanced

Performance

qwen3.5:4b vicuna:13b
Tokens/sec7.413.4
First chunk1815 msN/A
TTFT1.8 s438 ms
Load time10.9 s0.6 s
Memory usage3.5 GB10.3 GB
Memory %23%32%

HW Fit Score Breakdown

qwen3.5:4b

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

vicuna:13b

Speed
24/50
TTFT
30/20
Memory
30/30

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

vicuna:13b

Reasoning
7/20
Coding
5/20
Instruction
12/20
Structured
13/15
Math
3/15
Multilingual
8/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
View qwen3.5:4b details | View vicuna:13b 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