Back to leaderboard

spark-x2.5-4b

LM-STUDIO GGUF

spark2_5 · 4B · Q4_K_M

Good

Sep 30, 2026 · AMD Ryzen 7 4800H

qwen/qwen3.6-35b-a3b

LM-STUDIO MLX

qwen3_5_moe · 35B · 4bit

Excellent

Jul 17, 2026 · Apple M5 Max

Global Score
77 vs 89
Hardware Fit
90 vs 97
Quality Score
71 vs 86

Hardware

spark-x2.5-4b qwen/qwen3.6-35b-a3b
MachineASUSTeK COMPUTER INC. ROG Strix G513IM_G513IMMacBook Pro
CPUAMD Ryzen 7 4800HApple M5 Max
Cores1618
RAM15 GB64 GB
GPUAMD Radeon(TM) Graphics, NVIDIA GeForce RTX 3060 Laptop GPUApple M5 Max
OSMicrosoft Windows 11 Pro 10.0.26200macOS 27.0
Archx64arm64
Power Modebalancedbalanced

Performance

spark-x2.5-4b qwen/qwen3.6-35b-a3b
Tokens/sec48.9130.2
First chunk20 ms5 ms
TTFT168 ms135 ms
Load timeN/AN/A
Memory usage9.4 GB26.6 GB
Memory %61%42%

HW Fit Score Breakdown

spark-x2.5-4b

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

qwen/qwen3.6-35b-a3b

Speed
50/50
TTFT
20/20
Memory
27/30

Quality

spark-x2.5-4b

Reasoning
13/20
Coding
14/20
Instruction
16/20
Structured
15/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong

qwen/qwen3.6-35b-a3b

Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View spark-x2.5-4b details | View qwen/qwen3.6-35b-a3b 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