Back to leaderboard

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

LM-STUDIO GGUF

qwen35moe · 35B

Excellent

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

granite3.1-dense:2b

OLLAMA GGUF

granite · 2.5B · Q4_K_M

Good

Mar 2, 2026 · Apple M4

Global Score
86 vs 68
Hardware Fit
84 vs 100
Quality Score
87 vs 54

Hardware

qwen3.6-35b-a3b-nv… granite3.1-dense:2b
MachineMicro-Star International Co., Ltd. MS-7E51MacBook Air
CPUAMD Ryzen 7 9700X 8-Core ProcessorApple M4
Cores1610
RAM31 GB32 GB
GPUNVIDIA GeForce RTX 5080, AMD Radeon(TM) GraphicsApple M4
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.3
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3.6-35b-a3b-nv… granite3.1-dense:2b
Tokens/sec69.254.6
First chunk14 msN/A
TTFT238 ms121 ms
Load timeN/A0.4 s
Memory usage22.2 GB5.6 GB
Memory %71%18%

HW Fit Score Breakdown

qwen3.6-35b-a3b-nvfp4-d…

Speed
50/50
TTFT
20/20
Memory
14/30

granite3.1-dense:2b

Speed
40/50
TTFT
30/20
Memory
30/30

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

granite3.1-dense:2b

Reasoning
8/20
Coding
9/20
Instruction
13/20
Structured
14/15
Math
3/15
Multilingual
7/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
View qwen3.6-35b-a3b-nv… details | View granite3.1-dense:2b 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