qwen3.5:35b
OLLAMA GGUFqwen35moe · 36.0B · Q4_K_M
Mar 7, 2026 · Intel Core™ i5-14600KF
qwen3-next:80b-a3b-instruct-q4_K_M
OLLAMA GGUFqwen3next · 79.7B · Q4_K_M
Aug 18, 2026 · Intel Xeon® E5-2637 v3
Global Score
77 vs 78
Hardware Fit
53 vs 51
Quality Score
87 vs 89
Hardware
qwen3.5:35b qwen3-next:80b-a3b…
MachineASUSDell Inc. Precision Tower 7910
CPUIntel Core™ i5-14600KFIntel Xeon® E5-2637 v3
Cores2016
RAM32 GB96 GB
GPUNVIDIA GeForce RTX 4070 Ti SUPERNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060
OSMicrosoft Windows 11 Famille 10.0.26200Microsoft Windows 10 Pro 10.0.19045
Archx64x64
Power Modebalancedbalanced
Performance
qwen3.5:35b qwen3-next:80b-a3b…
Tokens/sec16.08.7
First chunk719 ms1251 ms
TTFT719 ms1.3 s
Load time17.8 s61.6 s
Memory usage25.0 GB48.3 GB
Memory %79%50%
HW Fit Score Breakdown
qwen3.5:35b
Speed
23/50
TTFT
20/20
Memory
10/30
qwen3-next:80b-a3b-inst…
Speed
9/50
TTFT
17/20
Memory
25/30
Quality
qwen3.5:35b
Reasoning
17/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen3-next:80b-a3b-inst…
Reasoning
18/20
Coding
19/20
Instruction
14/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest