qwen3.5:35b
OLLAMA GGUFqwen35moe · 36.0B · Q4_K_M
Mar 7, 2026 · Intel Core™ i5-14600KF
Sage-A1.5-Q4_K_M-GGUF:latest
OLLAMA GGUFqwen35moe · 35.5B · Q4_K_M
Oct 23, 2026 · AMD Ryzen 7 9700X 8-Core Processor
Global Score
77 vs 86
Hardware Fit
53 vs 86
Quality Score
87 vs 86
Hardware
qwen3.5:35b Sage-A1.5-Q4_K_M-G…
MachineASUSMicro-Star International Co., Ltd. MS-7E51
CPUIntel Core™ i5-14600KFAMD Ryzen 7 9700X 8-Core Processor
Cores2016
RAM32 GB31 GB
GPUNVIDIA GeForce RTX 4070 Ti SUPERNVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSMicrosoft Windows 11 Famille 10.0.26200Microsoft Windows 11 Pro 10.0.26300
Archx64x64
Power Modebalancedbalanced
Performance
qwen3.5:35b Sage-A1.5-Q4_K_M-G…
Tokens/sec16.075.2
First chunk719 ms168 ms
TTFT719 ms168 ms
Load time17.8 s0.0 s
Memory usage25.0 GB21.4 GB
Memory %79%69%
HW Fit Score Breakdown
qwen3.5:35b
Speed
23/50
TTFT
20/20
Memory
10/30
Sage-A1.5-Q4_K_M-GGUF:l…
Speed
50/50
TTFT
20/20
Memory
16/30
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
Sage-A1.5-Q4_K_M-GGUF:l…
Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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