Back to leaderboard

qwen3.5:2b

OLLAMA GGUF

qwen35 · 2.3B · Q8_0

Not Rec.

Apr 29, 2026 · Intel Core™ i5-8350U

llama3.1:8b

OLLAMA GGUF

llama · 8.0B · Q4_K_M

Good

Aug 25, 2026 · Apple M1 Pro

Global Score
13 vs 72
Hardware Fit
41 vs 77
Quality Score
1 vs 70

Hardware

qwen3.5:2b llama3.1:8b
MachineLENOVO 20L7CTO1WWMacBook Pro
CPUIntel Core™ i5-8350UApple M1 Pro
Cores810
RAM23 GB16 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Apple M1 Pro
OSFedora Linux 43macOS 26.6.2
Archx64arm64
Power Modelow-powerbalanced

Performance

qwen3.5:2b llama3.1:8b
Tokens/sec4.521.5
First chunk1413 ms368 ms
TTFT31.1 s368 ms
Load time7.1 s6.9 s
Memory usage3.8 GB12.9 GB
Memory %16%81%

HW Fit Score Breakdown

qwen3.5:2b

Speed
11/50
TTFT
0/20
Memory
30/30

llama3.1:8b

Speed
47/50
TTFT
20/20
Memory
10/30

Quality

qwen3.5:2b

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

llama3.1:8b

Reasoning
12/20
Coding
18/20
Instruction
13/20
Structured
13/15
Math
4/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3.5:2b details | View llama3.1:8b 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