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

unsloth-phi-4

LM-STUDIO MLX

llama · 4bit

Excellent

Mar 6, 2026 · Apple M4 Pro

Global Score
68 vs 82
Hardware Fit
59 vs 88
Quality Score
72 vs 80

Hardware

qwen2.5-coder:7b unsloth-phi-4
MachineASUSMac mini
CPUIntel Gen Intel® Core™ i7-13700KApple M4 Pro
Cores2414
RAM64 GB64 GB
GPUNVIDIA GeForce RTX 3070Apple M4 Pro
OSMicrosoft Windows 11 Pro 10.0.26200macOS 15.7.4
Archx64arm64
Power Modeunknownbalanced

Performance

qwen2.5-coder:7b unsloth-phi-4
Tokens/sec34.427.4
First chunk1991 ms457 ms
TTFT2.0 s457 ms
Load time40.6 sN/A
Memory usage5.0 GB7.7 GB
Memory %8%12%

HW Fit Score Breakdown

qwen2.5-coder:7b

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

unsloth-phi-4

Speed
38/50
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

unsloth-phi-4

Reasoning
15/20
Coding
19/20
Instruction
14/20
Structured
13/15
Math
9/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen2.5-coder:7b details | View unsloth-phi-4 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