gpt-oss:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Oct 2, 2026 · Cortex-X925
qwen3.5-35b-a3b-t48-c8k:latest
OLLAMA GGUFqwen35moe · 36.0B · Q4_K_M
Sep 6, 2026 · Intel Xeon® E5-4650 v2
Global Score
83 vs 81
Hardware Fit
64 vs 63
Quality Score
91 vs 88
Hardware
gpt-oss:120b qwen3.5-35b-a3b-t4…
MachineNVIDIA NVIDIA_DGX_SparkDell Inc. PowerEdge R820
CPUCortex-X925Intel Xeon® E5-4650 v2
Cores2080
RAM122 GB256 GB
GPUDevice 2e12Microsoft Remote Display Adapter, NVIDIA Tesla P4, NVIDIA Tesla P4, Microsoft Basic Display Adapter
OSUbuntu 24.04.5 LTSMicrosoft Windows Server 2022 Datacenter 10.0.20348
Archarm64x64
Power Modeperformancebalanced
Performance
gpt-oss:120b qwen3.5-35b-a3b-t4…
Tokens/sec28.617.2
First chunk422 ms845 ms
TTFT2.5 s845 ms
Load time9.9 s103.1 s
Memory usage60.1 GB21.9 GB
Memory %49%9%
HW Fit Score Breakdown
gpt-oss:120b
Speed
30/50
TTFT
9/20
Memory
25/30
qwen3.5-35b-a3b-t48-c8k…
Speed
16/50
TTFT
17/20
Memory
30/30
Quality
gpt-oss:120b
Reasoning
19/20
Coding
19/20
Instruction
14/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
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
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