Migtissera Tess 4 9B GGUF

--- quantized_by: bartowski pipeline_tag: image-text-to-text license: apache-2.0 tags: - tess - agentic - reasoning - thinking - long-context - tool-use - qwen3 - multimodal - conversational base_model: migtissera/Tess-4-9B base_model_relation: quantized --- ## Llamacpp imatrix Quantizations of Tess-4-9B by migtissera Using <a href="https://github.com/ggml-org/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggml-org/llama.cpp/releases/tag/b10032">b10032</a> for quantization. Original model: https://huggingface.co/migtissera/Tess-4-9B All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/82ae9b520227f57d79ba04add13d0d0d) Run them in your choice of tools: - [llama.cpp](https://github.com/ggml-org/llama.cpp) - [LM Studio](https://lmstudio.ai/) - [koboldcpp](https://github.com/LostRuins/koboldcpp) - [Jan AI](https://www.jan.ai/) - [Text Generation Web UI](https://github.com/oobabooga/text-generation-webui) - [LoLLMs](https://github.com/ParisNeo/lollms) Note: if it's a newly supported model, you may need to wait for an update from the developers. ## Prompt format ``` <|im_start|>system {system_prompt}<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant <think> ``` ## Download a file (not the whole branch) from below: | Filename | Quant type | File Size | Split | Description | | -------- | ---------- | --------- | ----- | ----------- | | [migtissera_Tess-4-9B-bf16.gguf](https://huggingface.co/bartowski/migtissera_Tess-4-9B-GGUF/blob/main/migtissera_Tess-4-9B-bf16.gguf) | bf16 | 18.41GB | false | Full BF16 weights. | | [migtissera_Tess-4-9B-Q8_0.gguf](https://huggingface.co/bartowski/migtissera_Tess-4-9B-GGUF/blob/main/migtissera_Tess-4-9B-Q8_0.gguf) | Q8_0 | 9.80GB | false | Extremely high quality, generally unneeded but max available quant. | | [migtissera_Tess-4-9B-Q6_K_L.gguf](https://huggingface.co/bartowski/migtissera_Tess-4-9B-GGUF/blob/main/migtissera_Tess-4-9B-Q6_K_L.gguf) | Q6_K_L | 8.33GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | | [migtissera_Tess-4-9B-Q6_K.gguf](https://huggingface.co/bartowski/migtissera_Tess-4-9B-GGUF/blob/main/migtissera_Tess-4-9B-Q6_K.gguf) | Q6_K | 7.84GB | false | Very high quality, near perfect, *recommended*. | | [migtissera_Tess-4-9B-Q5_K_L.gguf](https://huggingface.co/bartowski/mi...

Source context: 1394 downloads · 1 likes · Pipeline image-text-to-text · Repo bartowski/migtissera_Tess-4-9B-GGUF