Instructions to use Ailiance-fr/devstral-v3-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ailiance-fr/devstral-v3-sft with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/Devstral-Small-2507-unsloth-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "Ailiance-fr/devstral-v3-sft")

Transformers

How to use Ailiance-fr/devstral-v3-sft with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Ailiance-fr/devstral-v3-sft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Ailiance-fr/devstral-v3-sft", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Ailiance-fr/devstral-v3-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ailiance-fr/devstral-v3-sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ailiance-fr/devstral-v3-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ailiance-fr/devstral-v3-sft

SGLang

How to use Ailiance-fr/devstral-v3-sft with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Ailiance-fr/devstral-v3-sft" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ailiance-fr/devstral-v3-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Ailiance-fr/devstral-v3-sft" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ailiance-fr/devstral-v3-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use Ailiance-fr/devstral-v3-sft with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Ailiance-fr/devstral-v3-sft to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Ailiance-fr/devstral-v3-sft to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Ailiance-fr/devstral-v3-sft to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Ailiance-fr/devstral-v3-sft",
    max_seq_length=2048,
)

Docker Model Runner
How to use Ailiance-fr/devstral-v3-sft with Docker Model Runner:
```
docker model run hf.co/Ailiance-fr/devstral-v3-sft
```

devstral-v3-sft / README.md

clemsail

docs: add upstream base model official evaluations

7a1cb9f verified 2 days ago

preview code

raw

history blame contribute delete

8.9 kB

	---
	base_model: unsloth/Devstral-Small-2507-unsloth-bnb-4bit
	library_name: peft
	model_name: devstral-v3-sft
	tags:
	- base_model:adapter:unsloth/Devstral-Small-2507-unsloth-bnb-4bit
	- lora
	- sft
	- transformers
	- trl
	- unsloth
	license: apache-2.0
	pipeline_tag: text-generation
	---

	# Model Card for devstral-v3-sft

	This model is a fine-tuned version of [unsloth/Devstral-Small-2507-unsloth-bnb-4bit](https://huggingface.co/unsloth/Devstral-Small-2507-unsloth-bnb-4bit).
	It has been trained using [TRL](https://github.com/huggingface/trl).

	## Quick start

	```python
	from transformers import pipeline

	question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
	generator = pipeline("text-generation", model="None", device="cuda")
	output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
	print(output["generated_text"])
	```

	## Training procedure




	This model was trained with SFT.

	### Framework versions

	- PEFT 0.18.1
	- TRL: 0.24.0
	- Transformers: 5.5.0
	- Pytorch: 2.10.0
	- Datasets: 4.3.0
	- Tokenizers: 0.22.2

	## Citations



	Cite TRL as:

	```bibtex
	@misc{vonwerra2022trl,
	title = {{TRL: Transformer Reinforcement Learning}},
	author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
	year = 2020,
	journal = {GitHub repository},
	publisher = {GitHub},
	howpublished = {\url{https://github.com/huggingface/trl}}
	}
	```

	# devstral-v3-sft


	## 🇪🇺 EU AI Act transparency

	This model is published under the AI Act framework (Regulation EU 2024/1689).

	\| Field \| Value \|
	\|---\|---\|
	\| Provider \| Ailiance (clemsail) \|
	\| Role under AI Act \| GPAI provider \|
	\| Adapter type \| LoRA / PEFT — supervised fine-tune adapter \|
	\| Base model \| `mistralai/Devstral-Small-2-24B-Instruct-2512` \|
	\| License \| Apache-2.0 (this artefact); upstream Mistral licence applies separately \|
	\| Intended use \| Code generation across Python / Rust / TypeScript / C++ / SQL / shell, with stronger reasoning on engineering questions \|
	\| Out of scope \| Healthcare diagnosis, legal advice, autonomous safety-critical decisions, generation of malicious code or exploits \|
	\| Risk classification \| Limited risk — Article 50 transparency obligations apply \|
	\| Copyright respect \| Training data does not include scraped copyrighted material. Public engineering documentation under permissive licences plus internal synthetic distillation. \|
	\| Full provenance \| https://ailiance.fr/transparency \|
	\| Contact \| postmaster@saillant.cc \|

	⚠️ You are using an AI model. Outputs may be inaccurate, biased or
	fabricated. Do not act on them without independent verification, especially
	in regulated domains.

	## Benchmarks

	Run via `lm-eval-harness` v0.4.x against the FUSED checkpoint (base + this
	adapter merged for inference). Strict-match where applicable.

	\| Task \| Metric \| Score \|
	\|---\|---\|---\|
	\| gsm8k \| `exact_match,strict-match` \| 0.844 \|
	\| ifeval \| `prompt_level_strict_acc,none` \| 0.691 \|
	\| bbh_cot_fewshot \| `exact_match,get-answer` \| 0.795 \|
	\| bbh_cot_fewshot_boolean_expressions \| `exact_match,get-answer` \| 0.900 \|
	\| bbh_cot_fewshot_causal_judgement \| `exact_match,get-answer` \| 0.600 \|
	\| bbh_cot_fewshot_date_understanding \| `exact_match,get-answer` \| 0.933 \|
	\| bbh_cot_fewshot_disambiguation_qa \| `exact_match,get-answer` \| 0.767 \|
	\| bbh_cot_fewshot_dyck_languages \| `exact_match,get-answer` \| 0.100 \|
	\| bbh_cot_fewshot_formal_fallacies \| `exact_match,get-answer` \| 0.600 \|
	\| bbh_cot_fewshot_geometric_shapes \| `exact_match,get-answer` \| 0.367 \|
	\| bbh_cot_fewshot_hyperbaton \| `exact_match,get-answer` \| 1.000 \|
	\| bbh_cot_fewshot_logical_deduction_five_objects \| `exact_match,get-answer` \| 0.767 \|
	\| bbh_cot_fewshot_logical_deduction_seven_objects \| `exact_match,get-answer` \| 0.533 \|
	\| bbh_cot_fewshot_logical_deduction_three_objects \| `exact_match,get-answer` \| 0.900 \|
	\| bbh_cot_fewshot_movie_recommendation \| `exact_match,get-answer` \| 0.833 \|
	\| bbh_cot_fewshot_multistep_arithmetic_two \| `exact_match,get-answer` \| 0.867 \|
	\| bbh_cot_fewshot_navigate \| `exact_match,get-answer` \| 0.967 \|
	\| bbh_cot_fewshot_object_counting \| `exact_match,get-answer` \| 0.967 \|
	\| bbh_cot_fewshot_penguins_in_a_table \| `exact_match,get-answer` \| 0.933 \|
	\| bbh_cot_fewshot_reasoning_about_colored_objects \| `exact_match,get-answer` \| 0.967 \|
	\| bbh_cot_fewshot_ruin_names \| `exact_match,get-answer` \| 0.667 \|
	\| bbh_cot_fewshot_salient_translation_error_detection \| `exact_match,get-answer` \| 0.700 \|
	\| bbh_cot_fewshot_snarks \| `exact_match,get-answer` \| 0.700 \|
	\| bbh_cot_fewshot_sports_understanding \| `exact_match,get-answer` \| 0.900 \|
	\| bbh_cot_fewshot_temporal_sequences \| `exact_match,get-answer` \| 0.967 \|
	\| bbh_cot_fewshot_tracking_shuffled_objects_five_objects \| `exact_match,get-answer` \| 0.967 \|
	\| bbh_cot_fewshot_tracking_shuffled_objects_seven_objects \| `exact_match,get-answer` \| 0.933 \|
	\| bbh_cot_fewshot_tracking_shuffled_objects_three_objects \| `exact_match,get-answer` \| 0.967 \|
	\| bbh_cot_fewshot_web_of_lies \| `exact_match,get-answer` \| 1.000 \|
	\| bbh_cot_fewshot_word_sorting \| `exact_match,get-answer` \| 0.667 \|
	\| mmlu_pro \| `exact_match,custom-extract` \| 0.619 \|
	\| mmlu_pro_biology \| `exact_match,custom-extract` \| 0.768 \|
	\| mmlu_pro_business \| `exact_match,custom-extract` \| 0.660 \|
	\| mmlu_pro_chemistry \| `exact_match,custom-extract` \| 0.580 \|
	\| mmlu_pro_computer_science \| `exact_match,custom-extract` \| 0.676 \|
	\| mmlu_pro_economics \| `exact_match,custom-extract` \| 0.678 \|
	\| mmlu_pro_engineering \| `exact_match,custom-extract` \| 0.448 \|
	\| mmlu_pro_health \| `exact_match,custom-extract` \| 0.678 \|
	\| mmlu_pro_history \| `exact_match,custom-extract` \| 0.575 \|
	\| mmlu_pro_law \| `exact_match,custom-extract` \| 0.432 \|
	\| mmlu_pro_math \| `exact_match,custom-extract` \| 0.678 \|
	\| mmlu_pro_other \| `exact_match,custom-extract` \| 0.612 \|
	\| mmlu_pro_philosophy \| `exact_match,custom-extract` \| 0.549 \|
	\| mmlu_pro_physics \| `exact_match,custom-extract` \| 0.630 \|
	\| mmlu_pro_psychology \| `exact_match,custom-extract` \| 0.704 \|
	\| leaderboard_math_hard \| `exact_match,none` \| 0.341 \|
	\| leaderboard_math_algebra_hard \| `exact_match,none` \| 0.570 \|
	\| leaderboard_math_counting_and_prob_hard \| `exact_match,none` \| 0.252 \|
	\| leaderboard_math_geometry_hard \| `exact_match,none` \| 0.182 \|
	\| leaderboard_math_intermediate_algebra_hard \| `exact_match,none` \| 0.139 \|
	\| leaderboard_math_num_theory_hard \| `exact_match,none` \| 0.416 \|
	\| leaderboard_math_prealgebra_hard \| `exact_match,none` \| 0.523 \|
	\| leaderboard_math_precalculus_hard \| `exact_match,none` \| 0.126 \|

	Raw `results_*.json` files are committed under `evals/`.

	## Validated in `ailiance/ailiance-bench` v0.2

	This model is referenced in the [Ailiance benchmark suite](https://github.com/ailiance/ailiance-bench)
	(Phase 6 scoreboard, 7-task hardware-design evaluation).

	See the full scoreboard:
	[ailiance-bench README#scoreboard-lora-phase-6](https://github.com/ailiance/ailiance-bench#scoreboard-lora-phase-6--2026-05-11).

	## Upstream base model — official evaluations

	This LoRA fine-tunes [`mistralai/Devstral-Small-2-24B-Instruct-2512`](https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512),
	Mistral's coding-specialist LLM. Headline software-engineering benchmarks
	from the upstream model card:

	\| Benchmark \| Devstral Small 2 (24B) \| Devstral 2 (123B) \| DeepSeek v3.2 (671B) \| Claude Sonnet 4.5 \|
	\|--------------------------\|-----------------------:\|------------------:\|---------------------:\|------------------:\|
	\| SWE Bench Verified \| 68.0 % \| 72.2 % \| 73.1 % \| 77.2 % \|
	\| SWE Bench Multilingual \| 55.7 % \| 61.3 % \| 70.2 % \| 68.0 % \|
	\| Terminal Bench 2 \| 22.5 % \| 32.6 % \| 46.4 % \| 42.8 % \|

	(For reference, GPT-5.1 Codex High: 73.7 % SWE Verified · 52.8 % Terminal Bench 2.)

	Devstral Small 2 (24B) is competitive with much larger open models on
	SWE Bench Verified (e.g. matches GLM-4.6 at 355B). Architecture uses
	rope-scaling per Llama 4 + Scalable-Softmax ([arXiv:2501.19399](https://arxiv.org/abs/2501.19399)).

	Source: [official Devstral-Small-2-24B-Instruct-2512 model card](https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512).

	> Reading these alongside this LoRA: Devstral Small 2 is a strong
	> coding base. This LoRA inherits its SWE-Bench performance and adds
	> language- or domain-specific specialization.

	---
	base_model: unsloth/Devstral-Small-2507-unsloth-bnb-4bit
	library_name: peft
	model_name: devstral-v3-sft
	tags:
	- base_model:adapter:unsloth/Devstral-Small-2507-unsloth-bnb-4bit
	- lora
	- sft
	- transformers
	- trl
	- unsloth
	license: apache-2.0
	pipeline_tag: text-generation
	---

	# Model Card for devstral-v3-sft

	This model is a fine-tuned version of [unsloth/Devstral-Small-2507-unsloth-bnb-4bit](https://huggingface.co/unsloth/Devstral-Small-2507-unsloth-bnb-4bit).
	It has been trained using [TRL](https://github.com/huggingface/trl).

	## Quick start

	```python
	from transformers import pipeline

	question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
	generator = pipeline("text-generation", model="None", device="cuda")
	output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
	print(output["generated_text"])
	```

	## Training procedure




	This model was trained with SFT.

	### Framework versions

	- PEFT 0.18.1
	- TRL: 0.24.0
	- Transformers: 5.5.0
	- Pytorch: 2.10.0
	- Datasets: 4.3.0
	- Tokenizers: 0.22.2

	## Citations



	Cite TRL as:

	```bibtex
	@misc{vonwerra2022trl,
	title = {{TRL: Transformer Reinforcement Learning}},
	author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
	year = 2020,
	journal = {GitHub repository},
	publisher = {GitHub},
	howpublished = {\url{https://github.com/huggingface/trl}}
	}
	```

	# devstral-v3-sft


	## 🇪🇺 EU AI Act transparency

	This model is published under the AI Act framework (Regulation EU 2024/1689).

	\| Field \| Value \|
	\|---\|---\|
	\| Provider \| Ailiance (clemsail) \|
	\| Role under AI Act \| GPAI provider \|
	\| Adapter type \| LoRA / PEFT — supervised fine-tune adapter \|
	\| Base model \| `mistralai/Devstral-Small-2-24B-Instruct-2512` \|
	\| License \| Apache-2.0 (this artefact); upstream Mistral licence applies separately \|
	\| Intended use \| Code generation across Python / Rust / TypeScript / C++ / SQL / shell, with stronger reasoning on engineering questions \|
	\| Out of scope \| Healthcare diagnosis, legal advice, autonomous safety-critical decisions, generation of malicious code or exploits \|
	\| Risk classification \| Limited risk — Article 50 transparency obligations apply \|
	\| Copyright respect \| Training data does not include scraped copyrighted material. Public engineering documentation under permissive licences plus internal synthetic distillation. \|
	\| Full provenance \| https://ailiance.fr/transparency \|
	\| Contact \| postmaster@saillant.cc \|

	⚠️ You are using an AI model. Outputs may be inaccurate, biased or
	fabricated. Do not act on them without independent verification, especially
	in regulated domains.

	## Benchmarks

	Run via `lm-eval-harness` v0.4.x against the FUSED checkpoint (base + this
	adapter merged for inference). Strict-match where applicable.

	\| Task \| Metric \| Score \|
	\|---\|---\|---\|
	\| gsm8k \| `exact_match,strict-match` \| 0.844 \|
	\| ifeval \| `prompt_level_strict_acc,none` \| 0.691 \|
	\| bbh_cot_fewshot \| `exact_match,get-answer` \| 0.795 \|
	\| bbh_cot_fewshot_boolean_expressions \| `exact_match,get-answer` \| 0.900 \|
	\| bbh_cot_fewshot_causal_judgement \| `exact_match,get-answer` \| 0.600 \|
	\| bbh_cot_fewshot_date_understanding \| `exact_match,get-answer` \| 0.933 \|
	\| bbh_cot_fewshot_disambiguation_qa \| `exact_match,get-answer` \| 0.767 \|
	\| bbh_cot_fewshot_dyck_languages \| `exact_match,get-answer` \| 0.100 \|
	\| bbh_cot_fewshot_formal_fallacies \| `exact_match,get-answer` \| 0.600 \|
	\| bbh_cot_fewshot_geometric_shapes \| `exact_match,get-answer` \| 0.367 \|
	\| bbh_cot_fewshot_hyperbaton \| `exact_match,get-answer` \| 1.000 \|
	\| bbh_cot_fewshot_logical_deduction_five_objects \| `exact_match,get-answer` \| 0.767 \|
	\| bbh_cot_fewshot_logical_deduction_seven_objects \| `exact_match,get-answer` \| 0.533 \|
	\| bbh_cot_fewshot_logical_deduction_three_objects \| `exact_match,get-answer` \| 0.900 \|
	\| bbh_cot_fewshot_movie_recommendation \| `exact_match,get-answer` \| 0.833 \|
	\| bbh_cot_fewshot_multistep_arithmetic_two \| `exact_match,get-answer` \| 0.867 \|
	\| bbh_cot_fewshot_navigate \| `exact_match,get-answer` \| 0.967 \|
	\| bbh_cot_fewshot_object_counting \| `exact_match,get-answer` \| 0.967 \|
	\| bbh_cot_fewshot_penguins_in_a_table \| `exact_match,get-answer` \| 0.933 \|
	\| bbh_cot_fewshot_reasoning_about_colored_objects \| `exact_match,get-answer` \| 0.967 \|
	\| bbh_cot_fewshot_ruin_names \| `exact_match,get-answer` \| 0.667 \|
	\| bbh_cot_fewshot_salient_translation_error_detection \| `exact_match,get-answer` \| 0.700 \|
	\| bbh_cot_fewshot_snarks \| `exact_match,get-answer` \| 0.700 \|
	\| bbh_cot_fewshot_sports_understanding \| `exact_match,get-answer` \| 0.900 \|
	\| bbh_cot_fewshot_temporal_sequences \| `exact_match,get-answer` \| 0.967 \|
	\| bbh_cot_fewshot_tracking_shuffled_objects_five_objects \| `exact_match,get-answer` \| 0.967 \|
	\| bbh_cot_fewshot_tracking_shuffled_objects_seven_objects \| `exact_match,get-answer` \| 0.933 \|
	\| bbh_cot_fewshot_tracking_shuffled_objects_three_objects \| `exact_match,get-answer` \| 0.967 \|
	\| bbh_cot_fewshot_web_of_lies \| `exact_match,get-answer` \| 1.000 \|
	\| bbh_cot_fewshot_word_sorting \| `exact_match,get-answer` \| 0.667 \|
	\| mmlu_pro \| `exact_match,custom-extract` \| 0.619 \|
	\| mmlu_pro_biology \| `exact_match,custom-extract` \| 0.768 \|
	\| mmlu_pro_business \| `exact_match,custom-extract` \| 0.660 \|
	\| mmlu_pro_chemistry \| `exact_match,custom-extract` \| 0.580 \|
	\| mmlu_pro_computer_science \| `exact_match,custom-extract` \| 0.676 \|
	\| mmlu_pro_economics \| `exact_match,custom-extract` \| 0.678 \|
	\| mmlu_pro_engineering \| `exact_match,custom-extract` \| 0.448 \|
	\| mmlu_pro_health \| `exact_match,custom-extract` \| 0.678 \|
	\| mmlu_pro_history \| `exact_match,custom-extract` \| 0.575 \|
	\| mmlu_pro_law \| `exact_match,custom-extract` \| 0.432 \|
	\| mmlu_pro_math \| `exact_match,custom-extract` \| 0.678 \|
	\| mmlu_pro_other \| `exact_match,custom-extract` \| 0.612 \|
	\| mmlu_pro_philosophy \| `exact_match,custom-extract` \| 0.549 \|
	\| mmlu_pro_physics \| `exact_match,custom-extract` \| 0.630 \|
	\| mmlu_pro_psychology \| `exact_match,custom-extract` \| 0.704 \|
	\| leaderboard_math_hard \| `exact_match,none` \| 0.341 \|
	\| leaderboard_math_algebra_hard \| `exact_match,none` \| 0.570 \|
	\| leaderboard_math_counting_and_prob_hard \| `exact_match,none` \| 0.252 \|
	\| leaderboard_math_geometry_hard \| `exact_match,none` \| 0.182 \|
	\| leaderboard_math_intermediate_algebra_hard \| `exact_match,none` \| 0.139 \|
	\| leaderboard_math_num_theory_hard \| `exact_match,none` \| 0.416 \|
	\| leaderboard_math_prealgebra_hard \| `exact_match,none` \| 0.523 \|
	\| leaderboard_math_precalculus_hard \| `exact_match,none` \| 0.126 \|

	Raw `results_*.json` files are committed under `evals/`.

	## Validated in `ailiance/ailiance-bench` v0.2

	This model is referenced in the [Ailiance benchmark suite](https://github.com/ailiance/ailiance-bench)
	(Phase 6 scoreboard, 7-task hardware-design evaluation).

	See the full scoreboard:
	[ailiance-bench README#scoreboard-lora-phase-6](https://github.com/ailiance/ailiance-bench#scoreboard-lora-phase-6--2026-05-11).

	## Upstream base model — official evaluations

	This LoRA fine-tunes [`mistralai/Devstral-Small-2-24B-Instruct-2512`](https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512),
	Mistral's coding-specialist LLM. Headline software-engineering benchmarks
	from the upstream model card:

	\| Benchmark \| Devstral Small 2 (24B) \| Devstral 2 (123B) \| DeepSeek v3.2 (671B) \| Claude Sonnet 4.5 \|
	\|--------------------------\|-----------------------:\|------------------:\|---------------------:\|------------------:\|
	\| SWE Bench Verified \| 68.0 % \| 72.2 % \| 73.1 % \| 77.2 % \|
	\| SWE Bench Multilingual \| 55.7 % \| 61.3 % \| 70.2 % \| 68.0 % \|
	\| Terminal Bench 2 \| 22.5 % \| 32.6 % \| 46.4 % \| 42.8 % \|

	(For reference, GPT-5.1 Codex High: 73.7 % SWE Verified · 52.8 % Terminal Bench 2.)

	Devstral Small 2 (24B) is competitive with much larger open models on
	SWE Bench Verified (e.g. matches GLM-4.6 at 355B). Architecture uses
	rope-scaling per Llama 4 + Scalable-Softmax ([arXiv:2501.19399](https://arxiv.org/abs/2501.19399)).

	Source: [official Devstral-Small-2-24B-Instruct-2512 model card](https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512).

	> Reading these alongside this LoRA: Devstral Small 2 is a strong
	> coding base. This LoRA inherits its SWE-Bench performance and adds
	> language- or domain-specific specialization.