qwen3.5-35b-a3b-t48-c8k:latest
OLLAMA GGUFqwen35moe · 36.0B · Q4_K_M
Sep 6, 2026 · Intel Xeon® E5-4650 v2
GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
Global Score
81 vs 79
Hardware Fit
63 vs 47
Quality Score
88 vs 93
Hardware
qwen3.5-35b-a3b-t4… GPT-120B:120b
MachineDell Inc. PowerEdge R820HP OMEN 35L VALORANT Limited Edition Gaming Desktop PC
CPUIntel Xeon® E5-4650 v2Intel Core™ i7-14700F
Cores8028
RAM256 GB128 GB
GPUMicrosoft Remote Display Adapter, NVIDIA Tesla P4, NVIDIA Tesla P4, Microsoft Basic Display AdapterNVIDIA GeForce RTX 5080
OSMicrosoft Windows Server 2022 Datacenter 10.0.20348Microsoft Windows 11 Enterprise 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
qwen3.5-35b-a3b-t4… GPT-120B:120b
Tokens/sec17.218.2
First chunk845 ms1719 ms
TTFT845 ms3.9 s
Load time103.1 s50.9 s
Memory usage21.9 GB61.5 GB
Memory %9%48%
HW Fit Score Breakdown
qwen3.5-35b-a3b-t48-c8k…
Speed
16/50
TTFT
17/20
Memory
30/30
GPT-120B:120b
Speed
17/50
TTFT
5/20
Memory
25/30
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
GPT-120B:120b
Reasoning
19/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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