Back to leaderboard

qwen2.5-coder:7b

OLLAMA GGUF

qwen2 · 7.6B · Q4_K_M

Good

Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

Global Score
68 vs 64
Hardware Fit
59 vs 69
Quality Score
72 vs 62

Hardware

qwen2.5-coder:7b qwen3.5:4b
MachineASUSLENOVO 20U30029MB
CPUIntel Gen Intel® Core™ i7-13700KIntel Core™ i5-10210U
Cores248
RAM64 GB15 GB
GPUNVIDIA GeForce RTX 3070CometLake-U GT2 [UHD Graphics]
OSMicrosoft Windows 11 Pro 10.0.26200Pop 24.04 LTS
Archx64x64
Power Modeunknownperformance

Performance

qwen2.5-coder:7b qwen3.5:4b
Tokens/sec34.47.4
First chunk1991 ms1815 ms
TTFT2.0 s1.8 s
Load time40.6 s10.9 s
Memory usage5.0 GB3.5 GB
Memory %8%23%

HW Fit Score Breakdown

qwen2.5-coder:7b

Speed
38/50
TTFT
12/20
Memory
9/30

qwen3.5:4b

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

Quality

qwen2.5-coder:7b

Reasoning
11/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
9/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

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
View qwen2.5-coder:7b details | View qwen3.5:4b 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