Coding GGUF models

14916 GGUF models: models tuned for programming and code completion. Sizes run from 1M to 1780B parameters. The longest trained context is 3906K tokens.

Most downloadedNewestLargestLongest contextSmallest
KI
KiteResolve 20B
Kiteresolve · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
CodingTool use
NO
Noema 1.5 4B Fast
Noema · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
CodingReasoningTool use
QW
Qwen.Qwen3 Coder 30B A3B Instruct
Qwen · DevQuasar
Params30.5B
Context256K
Q4_K_M18.6 GB
CodingTool use
QW
Qwopus3.5 9B Coder
Qwopus · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
CodingReasoningTool use
QW
Qwen3 VL 12B Instruct Brainstorm20x
Qwen · mradermacher
Params11.9B
Context256K
Q4_K_M7.2 GB
CodingTool useVision
GE
Gemma 4 E2B Coder Uncensored
Gemma · minas2025
Params4.65B
Context128K
Smallest5.0 GB
CodingReasoningTool use
ST
Step 3.5 Flash GGUF Q4 K S
Step · stepfun-ai
Params197B
Context256K
Smallest111.5 GB
CodingReasoningTool use
LL
Llama-3-NeuralHercules-5.0-8B
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
Coding
QW
Qwen3.5 9B Fable 5 v1
Qwen · mradermacher
Params9.2B
Context256K
Q4_K_M5.8 GB
CodingReasoningTool use
GP
Gpt Oss 20b
gpt-oss · DavidAU
Params20.9B
Context128K
Smallest11.5 GB
CodingReasoningTool use
DE
Secure-deepseek-coder-v2-MoE
DeepSeek · mradermacher
Params15.7B
Context160K
Q4_K_M10.4 GB
Coding
QW
Qwen Coder 14b Vulrepair
Qwen · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
CodingTool use
NO
Nomic Embed Text v1.5
Nomic · gaianet
Params137M
Context2K
Q4_K_M0.1 GB
CodingEmbedding
RT
RTLCoder v1.1 gguf 4bit
Rtlcoder · ishorn5
Params7.24B
Context32K
Smallest4.1 GB
Coding
LL
Llama-3-8B-Instruct-Coder-v2
Llama · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
Coding
QW
Qwen Image 2.1
Qwen · hhfw
Params8.19B
Context256K
Smallest3.3 GB
CodingTool useVision
ST
STARK WEB 12B
Stark · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
Coding
LL
Llama3 8B Instruct Replete Adapted
Llama · QuantFactory
Params8.03B
Context8K
Q4_K_M4.9 GB
CodingTool use
LL
Scarlett Llama 3 8B
Llama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
Coding
QW
Qwen2.5 VL 3B Instruct Heretic
Qwen · mradermacher
Params3.09B
Context125K
Q4_K_M1.9 GB
CodingVision
MI
dolphin-2.9.1-mixtral-1x22b
Mistral · bartowski
Params22.2B
Context64K
Q4_K_M13.3 GB
CodingTool use
MA
Magidonia 24B v4.3 Heretic
Magidonia · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
CodingTool use
QW
Qwen3 MOE 6x6B Star Trek Universe Alpha D 256k Ctx 36B
Qwen · mradermacher
Params26.9B
Context256K
Q4_K_M16.3 GB
CodingReasoningTool use
PY
PyRUA Lean Coder v0.1 4B
Pyrua · mradermacher
Params4.33B
Context256K
Q4_K_M2.8 GB
CodingReasoningTool use
GE
Gemma 4 E4B It The DECKARD V2 Strong HERETIC UNCENSORED Thinking
Gemma · mradermacher
Params7.52B
Context128K
Q4_K_M5.3 GB
CodingReasoningRoleplay
QW
Qwen3.6 35B A3B Fable 5 Distill
Qwen · mradermacher
Params35.5B
Context256K
Q4_K_M21.7 GB
CodingReasoningTool use
IN
Internlm2_5 1_8b Chat
InternLM · gaianet
Params1.89B
Context32K
Q4_K_M1.2 GB
Coding
MI
MiniCPM5 2B Heretic Abliterated
MiniCPM · mradermacher
Params2.52B
Context128K
Q4_K_M1.6 GB
CodingReasoningTool use
QW
Qwen3.5 9B Claude Fable 5xMerge
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
CodingReasoningTool use
QW
Entry_Coder_05_V3_256K_Merged
Qwen · Secondchancee
Params494M
Context256K
Q4_K_M0.4 GB
CodingTool use

Other uses

Keep browsing