qwen3.5-35b-a3b-t48-c8k:latest
OLLAMA GGUFqwen35moe · 36.0B · Q4_K_M
Sep 6, 2026 · Intel Xeon® E5-4650 v2
qwen2.5:72b
OLLAMA GGUFqwen2 · 72.7B · Q4_K_M
Jun 27, 2026 · Cortex-X925
Global Score
81 vs 75
Hardware Fit
63 vs 50
Quality Score
88 vs 86
Hardware
qwen3.5-35b-a3b-t4… qwen2.5:72b
MachineDell Inc. PowerEdge R820NVIDIA NVIDIA_DGX_Spark
CPUIntel Xeon® E5-4650 v2Cortex-X925
Cores8020
RAM256 GB122 GB
GPUMicrosoft Remote Display Adapter, NVIDIA Tesla P4, NVIDIA Tesla P4, Microsoft Basic Display AdapterDevice 2e12
OSMicrosoft Windows Server 2022 Datacenter 10.0.20348Ubuntu 24.04.4 LTS
Archx64arm64
Power Modebalancedperformance
Performance
qwen3.5-35b-a3b-t4… qwen2.5:72b
Tokens/sec17.24.4
First chunk845 ms529 ms
TTFT845 ms529 ms
Load time103.1 s49.7 s
Memory usage21.9 GB54.0 GB
Memory %9%44%
HW Fit Score Breakdown
qwen3.5-35b-a3b-t48-c8k…
Speed
16/50
TTFT
17/20
Memory
30/30
qwen2.5:72b
Speed
4/50
TTFT
20/20
Memory
26/30
Quality
qwen3.5-35b-a3b-t48-c8k…
Reasoning
17/20
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
qwen2.5:72b
Reasoning
19/20
Coding
19/20
Instruction
12/20
Structured
14/15
Math
12/15
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