----------------------------------------------- - Update September 5th 2026 - -----------------------------------------------
Happy September to everyone!
Thank you for trying out and/or evaluating this release of MistralAI's Ministral-3-8B-Instruct GGUF Converted Model!
What's new?
New chat template! Yes, a new chat template that completely fixes any previous issues for llama.cpp users and retains higher performance than the originally made template for Ollama/Yollama users!
Fixed both F16 and F32 MMPROJ Multi-Modal Vision projectors. (Re-Uploaded with working projectors)
Uploaded custom, high-quality, new "GH05T" edition Quant files for this model!
(This is a brand new method I have been developing for some time, I sincerely hope you enjoy it!)
Custom GH05T Quants Added:
These offer significantly higher performance and quality of response over previously uploaded release files while remaining
similar or smaller in size!
Q2_K_L
Q3_K_XL
Q4_K_XL
Q5_K_XL
Q6_K_L
Q8_0_L
F16 (Floating Point 16-bit)
Additionally, Multi-Modal Vision Projectors are also available (mmproj)
F16 (Floating Point 16-bit)
F32 (Floating Point 32-bit)
New JINJA Tokenizer Chat-Template: (This template features a sliding context window of NINETY-NINE (99) messages. This can be adjusted per-individual requirements simply by altering the number 99 in the template higher or lower in numerical value)
jinja
1{%- set ns = namespace(remMessage=false, hasSys=false, injSystem=true) -%}
2{%- for msg in messages -%}
3 {%- if msg.role == "system" -%}
4 {%- set ns.hasSys = true -%}
5 {%- endif -%}
6{%- endfor -%}
7{%- for msg in messages -%}
8 {{- bos_token -}}
9 {%- if ns.injSystem -%}
10 [SYSTEM_PROMPT]
11 {%- if ns.hasSys -%}
12 {{- msg.content -}}
13 {%- else -%}
14 'Always follow instructions that the user provides...'
15 {%- endif -%}
16 [/SYSTEM_PROMPT]
17 {%- set ns.injSystem = false -%}
18 {%- endif -%}
19 {%- if (messages|length - loop.index0) < 99 -%}
20 {%- set ns.remMessage = true -%}
21 {%- endif -%}
22 {%- if ns.remMessage -%}
23 {%- if msg.role == "user" -%}
24 {{- '[INST]' -}}
25 {%- if msg.content is string -%}
26 {{- msg.content -}}
27 {%- else -%}
28 {%- for block in msg.content -%}
29 {%- if block.type == 'text' -%}
30 {{- block.text -}}
31 {%- elif block.type in ['image', 'image_url'] -%}
32 {{- '[IMG]' -}}
33 {%- endif -%}
34 {%- endfor -%}
35 {%- endif -%}
36 {{- '[/INST]' -}}
37 {%- elif msg.role == "assistant" -%}
38 {{- msg.content -}}
39 {%- endif -%}
40 {%- endif -%}
41 {{- eos_token -}}
42{%- endfor -%}
------------------------------------------------ - Model Details and Specifications: - ------------------------------------------------
Ministral-3 8B Instruct 2512 (GGUF)
This release contains:
GGUF converted and Quantized model files
(Compatible with:)
-------------------------- ---- Original Info ---- --------------------------
(Crossposted from the link in the above section: "Model Details"):
Ministral 3 8B Instruct 2512 BF16
The largest model in the Ministral 3 family, Ministral 3 8B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language model with vision capabilities.
This model is the instruct post-trained version, fine-tuned for instruction tasks, making it ideal for chat and instruction based use cases.
The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware. Ministral 3 8B can even be deployed locally, capable of fitting in 32GB of VRAM in BF16, and less than 24GB of RAM/VRAM when quantized.
You must not use this model in a manner that infringes, misappropriates, or otherwise violates any third party’s rights, including intellectual property rights.
