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
QW
Qwen2.5 Coder 7B Instruct
Qwen · QuantFactory
Params7.6B
Context32K
Q4_K_M4.7 GB
Coding
QW
Qwen3 Esper3 Reasoning Instruct 6B Brainstorm20x Enhanced E32
Qwen · mradermacher
Params5.94B
Context40K
Q4_K_M3.6 GB
CodingReasoning
QW
Qwen3.8 27B TURBO Fable Cold Fusion 735 882 Heretic Uncensored NEO CODER MAX MTP
Qwen · Humberto16
Params27B
Context256K
Q4_K_M18.0 GB
CodingReasoningRoleplay
QW
Qwen3 Coder 30B A3B Instruct
Qwen · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
Coding
TO
llm-agents_tora-code-34b-v1.0
Tora · TheBloke
Params33.7B
Context16K
Q4_K_M20.2 GB
Coding
GE
Gemma 4 31B Fable 5 Agent Distill
Gemma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
Coding
QW
Qwen2.5 VL 72B Instruct Heretic
Qwen · mradermacher
Params72.7B
Context125K
Q4_K_M47.4 GB
CodingVision
QW
Qwen2.5 Coder 32B Instruct AWQ
Qwen · EasierAI
Params32.8B
Context128K
Q4_K_M19.9 GB
Coding
DA
Dans PersonalityEngine v1.0.0 8b
Dans · bartowski
Params8B
Context128K
Q4_K_M4.9 GB
Coding
QW
Qwen3.6 27B Fable Fusion 711 Uncensored Heretic NM DAU NEO MAX MTP
Qwen · tatekuperus
Params27B
Context256K
Q4_K_M18.0 GB
CodingReasoningRoleplay
LF
LFM2 12B A1B SpeedDemon The Deckard II HERETIC Uncensored
Lfm · mradermacher
Params11.3B
Context125K
Q4_K_M6.8 GB
CodingRoleplay
LL
llama-3-sqlcoder-8b
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
Coding
PH
Phi 3 Mini 4k Instruct
Phi · SanctumAI
Params3.82B
Context4K
Q4_K_M2.4 GB
Coding
DE
Deepseek Wizard 33B slerp
DeepSeek · mradermacher
Params17.4B
Context16K
Q4_K_M10.5 GB
Coding
QW
Qwen2.5 Coder 32B Abliterated
Qwen · TobiasLogic
Params32.8B
Context32K
Q4_K_M19.9 GB
Coding
KA
KAT Coder V2.5 Dev 16GB MixedQuant
Kat · fooooooooooooooooooooooooooooooooooooooooo
Params34.7B
Context256K
Smallest15.0 GB
Coding
MI
nondzu_mistral-7b-codealpaca-lora
Mistral · TheBloke
Params7.24B
Context32K
Q4_K_M4.4 GB
Coding
JI
jina embeddings v4 text code
Jina · jinaai
Params3.1B
Context125K
Q4_K_M1.9 GB
CodingEmbedding
GR
granite-3b-code-base
Granite · mradermacher
Params3.48B
Context2K
Q4_K_M2.1 GB
Coding
LL
CodeLlama 7b Instruct Hf
Llama · mradermacher
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
QW
Qwen3 53B A3B TOTAL RECALL v1.4
Qwen · mradermacher
Params53B
Context40K
Q4_K_M32.1 GB
CodingReasoningTool use
ST
starcoder2-3b
StarCoder · second-state
Params3.03B
Context16K
Q4_K_M1.8 GB
Coding
QW
Qwen2.5 Coder 3B Instruct heretic
Qwen · saidutta69
Params3.1B
Context32K
Q4_K_M1.9 GB
CodingRoleplay
QW
Qwen3.8 27B
Qwen · arbonquants
Params26.9B
Context256K
Q4_K_M16.5 GB
CodingReasoningTool use
FL
Flint APEX I MiniPlus V2.1
Flint · IsValorum
Params39.8B
Context256K
Smallest15.9 GB
CodingReasoningTool use
LL
Llama-3_3-Nemotron-Super-49B-V1
Llama · unsloth
Params49.9B
Context128K
Q4_K_M30.2 GB
Coding
CO
Yi Coder 1.5B
Coder · QuantFactory
Params1.48B
Context128K
Q4_K_M1.0 GB
Coding
DO
Dots.Mocr
Dots · prithivMLmods
Params1.78B
Context128K
Q4_K_M1.1 GB
CodingVision
GR
Granite 3b Code Base 128k
Granite · mradermacher
Params3.48B
Context125K
Q4_K_M2.1 GB
Coding
DE
DeepSeek-Coder-V2-Lite-Instruct
DeepSeek · second-state
Params15.7B
Context160K
Q4_K_M10.4 GB
Coding

Other uses

Keep browsing