Back to leaderboard

qwen/qwen3.5-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q6_K

Not Rec.

Sep 19, 2026 · AMD Ryzen 7 5800X 8-Core Processor

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · 7.9B · Q4_K_M

Excellent

Oct 31, 2026 · AMD RYZEN AI MAX+ 395

Global Score
72 vs 81
Hardware Fit
35 vs 84
Quality Score
88 vs 79

Hardware

qwen/qwen3.5-35b-a3b google/gemma-4-e4b
MachineSystem manufacturerGMKtec EVO-X3
CPUAMD Ryzen 7 5800X 8-Core ProcessorAMD RYZEN AI MAX+ 395
Cores1632
RAM32 GB120 GB
GPUAMD Radeon RX 9060 XTAMD Radeon(TM) 8060S Graphics
OSMicrosoft Windows 11 Home 10.0.26200Microsoft Windows 11 Pro 10.0.26300
Archx64x64
Power Modebalancedbalanced

Performance

qwen/qwen3.5-35b-a3b google/gemma-4-e4b
Tokens/sec8.347.3
First chunk32 ms23 ms
TTFT2.0 s1.9 s
Load timeN/AN/A
Memory usage28.9 GB13.2 GB
Memory %91%11%

HW Fit Score Breakdown

qwen/qwen3.5-35b-a3b

Speed
13/50
TTFT
17/20
Memory
5/30

google/gemma-4-e4b

Speed
44/50
TTFT
10/20
Memory
30/30

Quality

qwen/qwen3.5-35b-a3b

Reasoning
16/20
Coding
19/20
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

google/gemma-4-e4b

Reasoning
14/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
View qwen/qwen3.5-35b-a3b details | View google/gemma-4-e4b 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