Back to leaderboard

qwen2.5-coder:1.5b

OLLAMA GGUF

qwen2 · 1.5B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

qwen3.5-35b-a3b-t48-c8k:latest

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Aug 23, 2026 · Intel Xeon® E5-4650 v2

Global Score
68 vs 78
Hardware Fit
100 vs 51
Quality Score
54 vs 89

Hardware

qwen2.5-coder:1.5b qwen3.5-35b-a3b-t4…
MachineLENOVO 20U30029MBDell Inc. PowerEdge R820
CPUIntel Core™ i5-10210UIntel Xeon® E5-4650 v2
Cores880
RAM15 GB256 GB
GPUCometLake-U GT2 [UHD Graphics]Microsoft Remote Display Adapter, Microsoft Basic Display Adapter
OSPop 24.04 LTSMicrosoft Windows Server 2022 Datacenter 10.0.20348
Archx64x64
Power Modelow-powerbalanced

Performance

qwen2.5-coder:1.5b qwen3.5-35b-a3b-t4…
Tokens/sec21.87.1
First chunk499 ms997 ms
TTFT499 ms997 ms
Load time4.4 s45.4 s
Memory usage1.5 GB21.6 GB
Memory %10%8%

HW Fit Score Breakdown

qwen2.5-coder:1.5b

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

qwen3.5-35b-a3b-t48-c8k…

Speed
6/50
TTFT
15/20
Memory
30/30

Quality

qwen2.5-coder:1.5b

Reasoning
8/20
Coding
11/20
Instruction
13/20
Structured
11/15
Math
3/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Strong

qwen3.5-35b-a3b-t48-c8k…

Reasoning
16/20
Coding
19/20
Instruction
17/20
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