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

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Jul 30, 2026 · Intel Xeon® E5-4620 0

mlx-community/meta-llama-3.1-8b-instruct

LM-STUDIO MLX

llama · 8B · 4bit

Good

Mar 5, 2026 · Apple M4 Pro

Global Score

10 vs 77

Hardware Fit

33 vs 100

Quality Score

0 vs 67

Hardware

qwen3.5-35b-a3b-t4… mlx-community/meta…

MachineDell Inc. PowerEdge R820Mac mini

CPUIntel Xeon® E5-4620 0Apple M4 Pro

Cores6414

RAM256 GB64 GB

GPUMicrosoft Remote Display Adapter, Microsoft Basic Display AdapterApple M4 Pro

OSMicrosoft Windows Server 2022 Datacenter 10.0.20348macOS 15.7.4

Archx64arm64

Power Modebalancedbalanced

Performance

qwen3.5-35b-a3b-t4… mlx-community/meta…

Tokens/sec3.554.3

First chunk3509 ms277 ms

TTFT30.0 s277 ms

Load time30.0 sN/A

Memory usage22.0 GB4.2 GB

Memory %9%7%

HW Fit Score Breakdown

qwen3.5-35b-a3b-t48-c8k…

Speed

3/50

TTFT

0/20

Memory

30/30

mlx-community/meta-llam…

Speed

50/50

TTFT

20/20

Memory

30/30

Quality

qwen3.5-35b-a3b-t48-c8k…

Reasoning

0/20

Coding

0/20

Instruction

0/20

Structured

0/15

Math

0/15

Multilingual

0/10

Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

mlx-community/meta-llam…

Reasoning

11/20

Coding

14/20

Instruction

14/20

Structured

15/15

Math

4/15

Multilingual

9/10

Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong

View qwen3.5-35b-a3b-t4… details | View mlx-community/meta… 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