deepseek-r1:7b
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Mar 5, 2026 · Intel Core™ i5-6500
qwen/qwen3.6-35b-a3b:2
LM-STUDIO GGUFqwen35moe · 35B · Q4_K_M
Sep 19, 2026 · AMD Ryzen 7 5800X 8-Core Processor
Global Score
66 vs 73
Hardware Fit
63 vs 50
Quality Score
67 vs 83
Hardware
deepseek-r1:7b qwen/qwen3.6-35b-a…
MachineGigabyte Technology Co., Ltd. H170M-D3HSystem manufacturer
CPUIntel Core™ i5-6500AMD Ryzen 7 5800X 8-Core Processor
Cores416
RAM16 GB31 GB
GPUGP104 [GeForce GTX 1070]Navi 44 [Radeon RX 9060 XT]
OSUbuntu 24.04.4 LTSUbuntu 26.04.1 LTS
Archx64x64
Power Modelow-powerlow-power
Performance
deepseek-r1:7b qwen/qwen3.6-35b-a…
Tokens/sec35.610.5
First chunk224 ms4 ms
TTFT7.5 s1.7 s
Load time7.7 sN/A
Memory usage4.6 GB21.4 GB
Memory %29%69%
HW Fit Score Breakdown
deepseek-r1:7b
Speed
50/50
TTFT
7/20
Memory
6/30
qwen/qwen3.6-35b-a3b:2
Speed
16/50
TTFT
18/20
Memory
16/30
Quality
deepseek-r1:7b
Reasoning
16/20
Coding
10/20
Instruction
9/20
Structured
10/15
Math
14/15
Multilingual
8/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Adequate Math: Strong Multilingual: Strong
qwen/qwen3.6-35b-a3b:2
Reasoning
16/20
Coding
15/20
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
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