Back to leaderboard

qwen3.5-0.8b-mlx

LM-STUDIO MLX

qwen3_5 · 0.8B · 4bit

Marginal

Mar 6, 2026 · Apple M4 Pro

qwen2.5-coder:7b

OLLAMA GGUF

qwen2 · 7.6B · Q4_K_M

Good

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

Global Score
53 vs 68
Hardware Fit
89 vs 59
Quality Score
38 vs 72

Hardware

qwen3.5-0.8b-mlx qwen2.5-coder:7b
MachineMac miniASUS
CPUApple M4 ProIntel Gen Intel® Core™ i7-13700K
Cores1424
RAM64 GB64 GB
GPUApple M4 ProNVIDIA GeForce RTX 3070
OSmacOS 15.7.4Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedunknown

Performance

qwen3.5-0.8b-mlx qwen2.5-coder:7b
Tokens/sec52.934.4
First chunk4013 ms1991 ms
TTFT4.0 s2.0 s
Load timeN/A40.6 s
Memory usage0.6 GB5.0 GB
Memory %1%8%

HW Fit Score Breakdown

qwen3.5-0.8b-mlx

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

qwen2.5-coder:7b

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

Quality

qwen3.5-0.8b-mlx

Reasoning
7/20
Coding
2/20
Instruction
12/20
Structured
10/15
Math
2/15
Multilingual
5/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Adequate

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
View qwen3.5-0.8b-mlx details | View qwen2.5-coder:7b 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