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

qwen3.6:35b-mlx

OLLAMA GGUF

nvfp4

Not Rec.

Jul 17, 2026 · Apple M5 Max

Global Score
68 vs 80
Hardware Fit
59 vs 77
Quality Score
72 vs 81

Hardware

qwen2.5-coder:7b qwen3.6:35b-mlx
MachineASUSMacBook Pro
CPUIntel Gen Intel® Core™ i7-13700KApple M5 Max
Cores2418
RAM64 GB48 GB
GPUNVIDIA GeForce RTX 3070Apple M5 Max
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.5.2
Archx64arm64
Power Modeunknownbalanced

Performance

qwen2.5-coder:7b qwen3.6:35b-mlx
Tokens/sec34.4129.8
First chunk1991 ms77 ms
TTFT2.0 s30.0 s
Load time40.6 s1.8 s
Memory usage5.0 GB19.7 GB
Memory %8%41%

HW Fit Score Breakdown

qwen2.5-coder:7b

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

qwen3.6:35b-mlx

Speed
50/50
TTFT
0/20
Memory
27/30

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

qwen3.6:35b-mlx

Reasoning
19/20
Coding
9/20
Instruction
18/20
Structured
11/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Strong Structured Output: Adequate Math: Strong Multilingual: Strong
View qwen2.5-coder:7b details | View qwen3.6:35b-mlx 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