Back to leaderboard

qwen3.5-0.8b-mlx

LM-STUDIO MLX

qwen3_5 · 0.8B · 4bit

Marginal

Mar 6, 2026 · Apple M4 Pro

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

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Sep 6, 2026 · Intel Xeon® E5-4650 v2

Global Score
53 vs 81
Hardware Fit
89 vs 63
Quality Score
38 vs 88

Hardware

qwen3.5-0.8b-mlx qwen3.5-35b-a3b-t4…
MachineMac miniDell Inc. PowerEdge R820
CPUApple M4 ProIntel Xeon® E5-4650 v2
Cores1480
RAM64 GB256 GB
GPUApple M4 ProMicrosoft Remote Display Adapter, NVIDIA Tesla P4, NVIDIA Tesla P4, Microsoft Basic Display Adapter
OSmacOS 15.7.4Microsoft Windows Server 2022 Datacenter 10.0.20348
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.5-0.8b-mlx qwen3.5-35b-a3b-t4…
Tokens/sec52.917.2
First chunk4013 ms845 ms
TTFT4.0 s845 ms
Load timeN/A103.1 s
Memory usage0.6 GB21.9 GB
Memory %1%9%

HW Fit Score Breakdown

qwen3.5-0.8b-mlx

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

qwen3.5-35b-a3b-t48-c8k…

Speed
16/50
TTFT
17/20
Memory
30/30

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

qwen3.5-35b-a3b-t48-c8k…

Reasoning
17/20
Coding
18/20
Instruction
16/20
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