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
MI
Devstral Small 2507 DASHQ Q2
Mistral · jkim96
Params23.6B
Context128K
Smallest6.8 GB
CodingTool use
JA
Jais Family 2p7b
Jais · mradermacher
Params2.95B
Context2K
Q4_K_M2.6 GB
Coding
DO
Dolphin v2
Dolphin · mradermacher
Params3.09B
Context125K
Q4_K_M1.9 GB
CodingTool useVision
SE
SEX ROLEPLAY V3 3.2 1B i1
Sex · mradermacher
Params1.5B
Context128K
Q4_K_M1.0 GB
CodingReasoningRoleplay
QW
SmartCode Fable 5 CoT Reasoning QKVO Qwen 3.6 27B Distilled
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
CodingReasoningTool use
NE
NextCoder 7B Finetuned
Nextcoder · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingTool use
ST
stablelm-2-12b
Stablelm · mradermacher
Params12.1B
Context4K
Q4_K_M7.4 GB
Coding
TI
TinyLlama 1.1B intermediate step 955k token 2T
Tinyllama · afrideva
Params1.1B
Context2K
Q4_K_M0.7 GB
Coding
TI
TinyLlama 1.1B Chat v0.5
Tinyllama · mradermacher
Params1.1B
Context2K
Q4_K_M0.7 GB
Coding
KW
Kwaipilot.KwaiCoder DS V2 Lite Base
Kwaicoder · csabakecskemeti
Params15.7B
Context160K
Q4_K_M10.4 GB
Coding
MI
Mistral Devstral 2505 CODER Brainstorm20x 34B
Mistral · mradermacher
Params34.1B
Context128K
Q4_K_M20.7 GB
CodingTool use
LL
Replete-Coder-Llama3-8B
Llama · BenevolenceMessiah
Params8.03B
Context8K
Q4_K_M4.9 GB
CodingTool use
IN
Industry Coder 27B v2.0
Industry · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
CodingReasoningTool use
QW
CursorCore QW2.5 7B
Qwen · QuantFactory
Params7.61B
Context32K
Q4_K_M4.7 GB
Coding
QW
Qwen2.5 Coder 32B Instruct Abliterated
Qwen · BenevolenceMessiah
Params32.8B
Context32K
Q4_K_M19.9 GB
CodingTool use
CO
Yi Coder 1.5B Chat
Coder · legraphista
Params1.48B
Context128K
Smallest0.5 GB
Coding
DA
DataSense GPU Full
Datasense · mradermacher
Params4.65B
Context128K
Q4_K_M3.4 GB
CodingReasoningTool use
QW
Logics Qwen3 Math 4B
Qwen · mradermacher
Params4.02B
Context16K
Q4_K_M2.5 GB
CodingReasoningTool use
YA
Yamase 12B
Yamase · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
CodingRoleplay
QW
Hemlock Qwen3.6 27B
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
CodingReasoningTool use
MI
dolphin-2.9.3-mistral-7B-32k
Mistral · huggingkot
Params7.25B
Context32K
Q4_K_M4.4 GB
CodingTool use
MI
MiniCPM5 2B
MiniCPM · Atomic-Germ
Params2.52B
Context128K
Q4_K_M1.6 GB
CodingReasoningTool use
QW
Qwen3 Coder 42B A3B Instruct TOTAL RECALL MASTER CODER M 512k Ctx
Qwen · mradermacher
Params42.4B
Context512K
Q4_K_M25.7 GB
CodingReasoningTool use
IN
Internvl3-38B
Internvl · unsloth
Params32.8B
Context32K
Q4_K_M19.8 GB
CodingTool useVision
QW
Qwen2.5 Hermes Instruct 1.5B
Qwen · koshuro
Params1.54B
Context32K
Q4_K_M1.0 GB
CodingTool use
HO
K2-Horizon-3.7B
Horizon · emperorofrome
Params5.06B
Context512K
Q4_K_M3.2 GB
CodingReasoningTool use
FL
FluentlyQwen2.5 32B i1
Fluentlyqwen · mradermacher
Params32.8B
Context32K
Q4_K_M19.9 GB
CodingReasoningRoleplay
RE
web doc refining lm
Redpj · QuantFactory
Params354M
Context2K
Q4_K_M0.2 GB
Coding
NE
Newton Bot 3
Newton · mradermacher
Params8.19B
Context128K
Q4_K_M5.0 GB
CodingTool use
VI
Viper Coder 7B Elite14
Viper · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingReasoningTool use

Other uses

Keep browsing