qwen3.5-35b-a3b-t48-c8k:latest
OLLAMA GGUFqwen35moe · 36.0B · Q4_K_M
Sep 6, 2026 · Intel Xeon® E5-4650 v2
llama3.2:1b
OLLAMA GGUFllama · 1.2B · Q8_0
Jun 26, 2026 · Cortex-A78AE
Global Score
81 vs 63
Hardware Fit
63 vs 100
Quality Score
88 vs 47
Hardware
qwen3.5-35b-a3b-t4… llama3.2:1b
MachineDell Inc. PowerEdge R820NVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUIntel Xeon® E5-4650 v2Cortex-A78AE
Cores806
RAM256 GB7 GB
GPUMicrosoft Remote Display Adapter, NVIDIA Tesla P4, NVIDIA Tesla P4, Microsoft Basic Display AdapterIntegrated / Unknown
OSMicrosoft Windows Server 2022 Datacenter 10.0.20348Ubuntu 22.04.5 LTS
Archx64arm64
Power Modebalancedbalanced
Performance
qwen3.5-35b-a3b-t4… llama3.2:1b
Tokens/sec17.240.2
First chunk845 ms1087 ms
TTFT845 ms1.1 s
Load time103.1 s6.2 s
Memory usage21.9 GB1.4 GB
Memory %9%19%
HW Fit Score Breakdown
qwen3.5-35b-a3b-t48-c8k…
Speed
16/50
TTFT
17/20
Memory
30/30
llama3.2:1b
Speed
50/50
TTFT
20/20
Memory
30/30
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
llama3.2:1b
Reasoning
4/20
Coding
9/20
Instruction
14/20
Structured
13/15
Math
1/15
Multilingual
6/10
Reasoning: Poor Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
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