Category
Uncensored AI for coding: what to check, and what is not measured
Most coding work never hits a refusal. When it does, it is usually security tooling, reverse engineering or code that touches sensitive data. This page lists what to check and keeps measured and claimed abilities apart.
Short answer
For coding, pick a refusal-reduced variant of a base model that is already good at code for your languages, with enough context for your repository and working tool calls if you use an agent. Refusal reduction does not make a model better at code. Atlas has not yet measured any model on coding tasks, so nothing on this page is a ranking.
Measured: nothing yet. Our coding study is designed but not run. See the benchmark methodology for what it will measure. Until then, test candidates on your own tasks.
Criteria that matter for code
| Criterion | Why it matters | Where Atlas shows it | Status |
|---|---|---|---|
| Base model coding ability | Abliteration and most uncensoring keep the base model's skills at best. Start from a strong base. | Base model cards (developer benchmarks) | Claimed by developer |
| Context window | Repository-scale prompts need long context, and providers often cap it below the model's configuration. | Config context per model; context limit per provider | Sourced |
| Tool calling | Coding agents depend on reliable function calls. A provider can accept tools while the model handles them poorly. | Card tags; provider feature tables | Sourced Quality not measured |
| Reasoning mode | Thinking modes help on hard tasks but spend output tokens, which you pay for. | Card tags and notes | Sourced |
| Pass rate on your tasks | The only number that predicts your results. | How to measure it yourself | Not measured |
| Cost per solved task | Cheap tokens can cost more if a model needs many attempts. | Token cost calculator | Not measured |
Creator coding claims
2 catalogued variants are positioned for coding by the creator: GLM-4.7-Flash Uncensored HauhauCS Balanced (GGUF); Gemma4-26B-A4B-QAT Uncensored HauhauCS Balanced (GGUF). The cards give no task-level results for these claims. Treat them as a reason to include the model in your own test, not as evidence.
Candidates by card features
Models whose card states a reasoning mode, tool use or a coding focus. Inclusion is not a recommendation.
Showing 18 of 18 candidates. Unknown values sort last.
| Model | Type | Params | Config context | License tag | Formats | Hosted API |
|---|---|---|---|---|---|---|
| dealignai GLM-5.3-Flash UNCENSORED FP8 dealignai/GLM-5.3-Flash-UNCENSORED-FP8 | Undisclosed | 321B 18B active | Not stated | MIT | None listed | |
| Dolphin Mistral 24B Venice Edition dphn/Dolphin-Mistral-24B-Venice-Edition | Fine-tuned | 24B | 128K | Apache 2.0 | Featherless, OpenRouter, Venice | |
| Gemma 4 26B A4B (instruction-tuned) google/gemma-4-26B-A4B-it | Base model | 25.2B 3.8B active | 256K | Apache 2.0 | Featherless, OpenRouter, Venice | |
| Gemma 4 26B A4B heretic (coder3101) coder3101/gemma-4-26B-A4B-it-heretic | Heretic | 25.8B 3.8B active | Not stated | Apache 2.0 | Featherless, Venice | |
| Gemma 4 26B A4B ultra-uncensored heretic (llmfan46) llmfan46/gemma-4-26B-A4B-it-ultra-uncensored-heretic | Heretic | 25.8B 3.8B active | 256K | Apache 2.0 | Featherless | |
| Gemma4-26B-A4B-QAT Uncensored HauhauCS Balanced (GGUF) HauhauCS/Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-MTP | Undisclosed | 25.2B 3.8B active | 256K | Gemma Terms of Use | None listed | |
| GLM-4.7-Flash zai-org/GLM-4.7-Flash | Base model | 31.2B 3B active | 198K | MIT | Featherless, OpenRouter | |
| GLM-4.7-Flash heretic (Olafangensan) Olafangensan/GLM-4.7-Flash-heretic | Heretic | 29.9B 3B active | Not stated | MIT | Venice | |
| GLM-4.7-Flash Uncensored HauhauCS Balanced (GGUF) HauhauCS/GLM-4.7-Flash-Uncensored-HauhauCS-Balanced | Undisclosed | 29.9B 3B active | 198K | MIT | None listed | |
| GLM-5.3-Flash zai-org/GLM-5.3-Flash | Base model | 320B 18B active | 1M (1,048,576) | MIT | OpenRouter, Venice | |
| gpt-oss-20b heretic (p-e-w) p-e-w/gpt-oss-20b-heretic | Heretic | 20.9B | 128K | Apache 2.0 | None listed | |
| Huihui Gemma 4 26B A4B abliterated huihui-ai/Huihui-gemma-4-26B-A4B-it-abliterated | Abliterated | 25.8B 3.8B active | 256K | Apache 2.0 | None listed | |
| Huihui Gemma 4 26B A4B QAT abliterated (GGUF) huihui-ai/Huihui-gemma-4-26B-A4B-it-qat-q4_0-unquantized-abliterated-GGUF | Abliterated | 25.2B 3.8B active | 256K | Apache 2.0 | None listed | |
| Huihui GLM-4.7-Flash abliterated huihui-ai/Huihui-GLM-4.7-Flash-abliterated | Abliterated | 31.2B 3B active | 198K | MIT | None listed | |
| Huihui GLM-5.3-Flash abliterated (GGUF) huihui-ai/Huihui-GLM-5.3-Flash-abliterated-GGUF | Abliterated | 321B 18B active | 1M (1,048,576) | MIT | None listed | |
| Huihui Qwen3.8-27B abliterated huihui-ai/Huihui-Qwen3.8-27B-abliterated | Abliterated | 27.8B | 256K | Apache 2.0 | Featherless | |
| Qwen3.8-27B Qwen/Qwen3.8-27B | Base model | 27B | 256K | Apache 2.0 | Featherless, OpenRouter, Venice | |
| Qwen3.8-27B Uncensored HauhauCS Aggressive (GGUF) HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF | Undisclosed | 27B | 256K | Apache 2.0 | None listed |
dealignai GLM-5.3-Flash UNCENSORED FP8
Undiscloseddealignai/GLM-5.3-Flash-UNCENSORED-FP8- Params
- 321B
- Context
- Not stated
- License
- MIT
- Hosted API
- None listed
Dolphin Mistral 24B Venice Edition
Fine-tuneddphn/Dolphin-Mistral-24B-Venice-Edition- Params
- 24B
- Context
- 128K
- License
- Apache 2.0
- Hosted API
- Featherless, OpenRouter, Venice
Gemma 4 26B A4B (instruction-tuned)
Base modelgoogle/gemma-4-26B-A4B-it- Params
- 25.2B
- Context
- 256K
- License
- Apache 2.0
- Hosted API
- Featherless, OpenRouter, Venice
- coder3101/gemma-4-26B-A4B-it-heretic
- Params
- 25.8B
- Context
- Not stated
- License
- Apache 2.0
- Hosted API
- Featherless, Venice
- llmfan46/gemma-4-26B-A4B-it-ultra-uncensored-heretic
- Params
- 25.8B
- Context
- 256K
- License
- Apache 2.0
- Hosted API
- Featherless
- HauhauCS/Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-MTP
- Params
- 25.2B
- Context
- 256K
- License
- Gemma Terms of Use
- Hosted API
- None listed
GLM-4.7-Flash
Base modelzai-org/GLM-4.7-Flash- Params
- 31.2B
- Context
- 198K
- License
- MIT
- Hosted API
- Featherless, OpenRouter
- Olafangensan/GLM-4.7-Flash-heretic
- Params
- 29.9B
- Context
- Not stated
- License
- MIT
- Hosted API
- Venice
- HauhauCS/GLM-4.7-Flash-Uncensored-HauhauCS-Balanced
- Params
- 29.9B
- Context
- 198K
- License
- MIT
- Hosted API
- None listed
GLM-5.3-Flash
Base modelzai-org/GLM-5.3-Flash- Params
- 320B
- Context
- 1M (1,048,576)
- License
- MIT
- Hosted API
- OpenRouter, Venice
gpt-oss-20b heretic (p-e-w)
Hereticp-e-w/gpt-oss-20b-heretic- Params
- 20.9B
- Context
- 128K
- License
- Apache 2.0
- Hosted API
- None listed
Huihui Gemma 4 26B A4B abliterated
Abliteratedhuihui-ai/Huihui-gemma-4-26B-A4B-it-abliterated- Params
- 25.8B
- Context
- 256K
- License
- Apache 2.0
- Hosted API
- None listed
- huihui-ai/Huihui-gemma-4-26B-A4B-it-qat-q4_0-unquantized-abliterated-GGUF
- Params
- 25.2B
- Context
- 256K
- License
- Apache 2.0
- Hosted API
- None listed
Huihui GLM-4.7-Flash abliterated
Abliteratedhuihui-ai/Huihui-GLM-4.7-Flash-abliterated- Params
- 31.2B
- Context
- 198K
- License
- MIT
- Hosted API
- None listed
Huihui GLM-5.3-Flash abliterated (GGUF)
Abliteratedhuihui-ai/Huihui-GLM-5.3-Flash-abliterated-GGUF- Params
- 321B
- Context
- 1M (1,048,576)
- License
- MIT
- Hosted API
- None listed
Huihui Qwen3.8-27B abliterated
Abliteratedhuihui-ai/Huihui-Qwen3.8-27B-abliterated- Params
- 27.8B
- Context
- 256K
- License
- Apache 2.0
- Hosted API
- Featherless
Qwen3.8-27B
Base modelQwen/Qwen3.8-27B- Params
- 27B
- Context
- 256K
- License
- Apache 2.0
- Hosted API
- Featherless, OpenRouter, Venice
- HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF
- Params
- 27B
- Context
- 256K
- License
- Apache 2.0
- Hosted API
- None listed