qwen3.6-35b-a3b-nvfp4-dspark-v2@?

LM-STUDIO GGUF

qwen35moe · 35B

Excellent

Aug 20, 2026 · AMD Ryzen 7 9700X 8-Core Processor

hf.co/LiquidAI/LFM2.5-2.6B-GGUF:F16

OLLAMA GGUF

lfm2 · 2.7B · unknown

Good

Aug 25, 2026 · Apple M1 Pro

Global Score

86 vs 61

Hardware Fit

84 vs 97

Quality Score

87 vs 46

Hardware

qwen3.6-35b-a3b-nv… hf.co/LiquidAI/LFM…

MachineMicro-Star International Co., Ltd. MS-7E51MacBook Pro

CPUAMD Ryzen 7 9700X 8-Core ProcessorApple M1 Pro

Cores1610

RAM31 GB16 GB

GPUNVIDIA GeForce RTX 5080, AMD Radeon(TM) GraphicsApple M1 Pro

OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.6.2

Archx64arm64

Power Modebalancedbalanced

Performance

qwen3.6-35b-a3b-nv… hf.co/LiquidAI/LFM…

Tokens/sec69.231.0

First chunk14 ms129 ms

TTFT238 ms129 ms

Load timeN/A3.5 s

Memory usage22.2 GB6.6 GB

Memory %71%41%

HW Fit Score Breakdown

qwen3.6-35b-a3b-nvfp4-d…

Speed

50/50

TTFT

20/20

Memory

14/30

hf.co/LiquidAI/LFM2.5-2…

Speed

50/50

TTFT

20/20

Memory

27/30

Quality

qwen3.6-35b-a3b-nvfp4-d…

Reasoning

16/20

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

hf.co/LiquidAI/LFM2.5-2…

Reasoning

14/20

Coding

13/20

Instruction

3/20

Structured

0/15

Math

14/15

Multilingual

2/10

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

View qwen3.6-35b-a3b-nv… details | View hf.co/LiquidAI/LFM… 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