smollm2-135m-instruct
LM-STUDIO GGUFllama · 135M · Q4_K_M
Mar 6, 2026 · Intel Core™ i5-5300U
qwen3.8-27b-uncensored-ymq-mtp
LM-STUDIO GGUFqwen35 · 27B
Sep 12, 2026 · AMD Ryzen 5 5600X 6-Core Processor
Global Score
38 vs 84
Hardware Fit
98 vs 81
Quality Score
12 vs 85
Hardware
smollm2-135m-instr… qwen3.8-27b-uncens…
MachineLENOVO 20BUS00700Gigabyte Technology Co., Ltd. X570 AORUS PRO
CPUIntel Core™ i5-5300UAMD Ryzen 5 5600X 6-Core Processor
Cores412
RAM16 GB32 GB
GPUIntel(R) HD Graphics 5500NVIDIA GeForce RTX 5070 Ti
OSMicrosoft Windows 10 Professionnel 10.0.19045Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
smollm2-135m-instr… qwen3.8-27b-uncens…
Tokens/sec39.318.3
First chunk573 ms9 ms
TTFT573 ms522 ms
Load timeN/A7.7 s
Memory usage0.1 GB14.9 GB
Memory %1%47%
HW Fit Score Breakdown
smollm2-135m-instruct
Speed
50/50
TTFT
20/20
Memory
28/30
qwen3.8-27b-uncensored-…
Speed
35/50
TTFT
20/20
Memory
26/30
Quality
smollm2-135m-instruct
Reasoning
2/20
Coding
1/20
Instruction
5/20
Structured
3/15
Math
0/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor
qwen3.8-27b-uncensored-…
Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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