FitMyLLM
Agentica/Dense

ADeepCoder 14B

DeepCoder 14B — specialized for code generation and reasoning tasks.

codingreasoningDistilled
14.8B
Parameters
128K
Context length
8
Benchmarks
10
Quantizations
30K
HF downloads
Architecture
Dense
Released
2025-04-16
Layers
48
KV Heads
8
Head Dim
128
Family
other

Quantization Options

Context length:
QuantBitsVRAM @ 16KQuality
Q3_K_M4
10.1 GB
7.9 + 2.3 KV
low
Q3_K_L4.3
10.7 GB
8.4 + 2.3 KV
moderate
IQ4_XS4.46
11.0 GB
8.7 + 2.3 KV
moderate
Q4_K_S4.67
11.4 GB
9.1 + 2.3 KV
moderate
Q4_K_M4.89
11.8 GB
9.5 + 2.3 KV
good
Q5_K_S5.57
13.0 GB
10.8 + 2.3 KV
good
Q5_K_M5.7
13.3 GB
11.0 + 2.3 KV
good
Q6_K6.56
14.9 GB
12.6 + 2.3 KV
excellent
Q8_08.5
18.5 GB
16.2 + 2.3 KV
lossless
FP1616
32.3 GB
30.1 + 2.3 KV
lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

Deploying for a team or in production? Size GPUs, cost & scaling in Enterprise →
READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN DEEPCODER 14B NOW

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (8)

HumanEval82.0
MBPP75.0
IFEval65.0
BBH28.5
MMLU-PRO28.3
MATH12.2
MUSR11.7
GPQA6.5

Run this model

Easiest way to get started·Beginners
DOCS ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run other:15b-q4_K_M

Tag may need adjustment — check ollama.com/library/other for available tags.

▸ SETUP GUIDE
>_

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more
Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

NVIDIA CMP 170HX 10 GB
10 GB VRAM • 1560 GB/s
NVIDIA
NVIDIA CMP 50HX
10 GB VRAM • 560 GB/s
NVIDIA
NVIDIA CMP 90HX
10 GB VRAM • 760 GB/s
NVIDIA
NVIDIA Tesla K40c
12 GB VRAM • 288 GB/s
NVIDIA
NVIDIA Tesla K40d
12 GB VRAM • 288 GB/s
NVIDIA
NVIDIA Tesla K40m
12 GB VRAM • 288 GB/s
NVIDIA

Find the best GPU for DeepCoder 14B

Build Hardware for DeepCoder 14B

DeepCoder 14B — specialized for code generation and reasoning tasks.

▸ SPEC SHEET

DeepCoder 14B14.8B Dense.

▸ SPECIFICATIONS
PARAMETERS
14.8B
ARCHITECTURE
Dense Transformer
CONTEXT LENGTH
128K tokens
CAPABILITIES
coding, reasoning
RELEASE DATE
2025-04-16
PROVIDER
Agentica
FAMILY
other
▸ VRAM REQUIREMENTS
QUANTBPWVRAMQUALITY
Q3_K_M47.9 GB88%
Q3_K_L4.38.4 GB90%
IQ4_XS4.468.7 GB92%
Q4_K_S4.679.1 GB93%
Q4_K_M4.899.5 GB94%
Q5_K_S5.5710.8 GB96%
Q5_K_M5.711.0 GB96%
Q6_K6.5612.6 GB97%
Q8_08.516.2 GB100%
FP161630.1 GB100%
§ 01BENCHMARK SCORES
HumanEval82.0
MMLU-PRO28.3
MATH12.2
IFEval65.0
BBH28.5
GPQA6.5
MUSR11.7
MBPP75.0
§ 03COMPATIBLE GPUs
30 @ Q4_K_M