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

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Aug 1, 2026 · Intel Xeon® E5-4620 0

qwen3-4b-qwen3.6-plus-reasoning-distilled

LM-STUDIO GGUF

qwen3 · 4B · Q4_1

Good

Apr 21, 2026 · Apple M2 Max

Global Score

65 vs 65

Hardware Fit

38 vs 96

Quality Score

76 vs 51

Hardware

qwen3.5-35b-a3b-t4… qwen3-4b-qwen3.6-p…

MachineDell Inc. PowerEdge R820Mac Studio

CPUIntel Xeon® E5-4620 0Apple M2 Max

Cores6412

RAM256 GB96 GB

GPUMicrosoft Remote Display Adapter, Microsoft Basic Display AdapterApple M2 Max

OSMicrosoft Windows Server 2022 Datacenter 10.0.20348macOS 26.1

Archx64arm64

Power Modebalancedbalanced

Performance

qwen3.5-35b-a3b-t4… qwen3-4b-qwen3.6-p…

Tokens/sec3.499.6

First chunk4210 ms18 ms

TTFT4.2 s1.6 s

Load time45.1 s4.8 s

Memory usage22.0 GB0.3 GB

Memory %9%0%

HW Fit Score Breakdown

qwen3.5-35b-a3b-t48-c8k…

Speed

3/50

TTFT

5/20

Memory

30/30

qwen3-4b-qwen3.6-plus-r…

Speed

50/50

TTFT

16/20

Memory

30/30

Quality

qwen3.5-35b-a3b-t48-c8k…

Reasoning

16/20

Coding

15/20

Instruction

9/20

Structured

15/15

Math

11/15

Multilingual

10/10

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

qwen3-4b-qwen3.6-plus-r…

Reasoning

8/20

Coding

4/20

Instruction

14/20

Structured

9/15

Math

8/15

Multilingual

8/10

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

View qwen3.5-35b-a3b-t4… details | View qwen3-4b-qwen3.6-p… 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