Model reference · open weights
AfriqueQwen3.5-ExtendedCM is an open-weight language model from McGill-NLP, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
AfriqueQwen3.5-4B-ExtendedCM Model Overview AfriqueQwen3.5-4B-ExtendedCM is part of the AfriqueLLM suite, a collection of open language models adapted to 20 African languages through continued pre-training (CPT) on ~34B tokens. This model is based on Qwen/Qwen3.5-4B-Base and has been specifically adapted for improved performance on African languages while maintaining strong capabilities in high-resource languages. This is an extended continued pre-training variant of AfriqueQwen3.5-4B, trained with 5x more code and math data (5B tokens each of CornStack-Python and FineMath, compared to 1B each in the standard version). This results in modest additional gains on reasoning-related benchmarks. Key Features - Type: Causal Language Model (Base/Pre-trained) - Base Model: Qwen 3.5 4B - Parameters: 4B - Context Length: 32,768 tokens (native) - Training Tokens: ~34B tokens of carefully curated multilingual data Supported Languages AfriqueQwen3.5-4B-ExtendedCM has been adapted for the following 20 African languages: High-resource languages used for catastrophic forgetting mitigation: English, French, Portuguese, Arabic Training Data Our training corpus combines multiple high-quality sources: - African Monolingual Data (~22.8B tokens): FineWeb2, WURA, and MADLAD-400 - Code (~1B tokens): CornStack-Python for reasoning capabilities - Mathematics (~1B tokens): FineMath-4+ for mathematical understanding - Synthetic Data (~324M tokens): GPT-4.1 translated domain-specific content across 10 domains We use UniMax sampling to create a balanced distribution, capping high-resource languages at approximately 1B tokens and upsampling lower-resource languages for up to five epochs. Quickstart Deployment For deployment, you can use vllm or sglang to create an OpenAI-compatible API endpoint: vLLM: SGLang: Training Details Hyperparameters - Learning Rate: 5e-5 (with warmup and cosine decay) - Context Length: 16,384 tokens - Optimizer: AdamW - Precision: BF16 mixed precision Infrastructure Training was conducted using the LLaMA-Factory framework on up to 64 NVIDIA H100 GPUs with: - DeepSpeed ZeRO-1/ZeRO-2 - Flash Attention 3 - Sequence packing - Liger Kernel optimizations Evaluation All Afr
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | McGill-NLP |
|---|---|
| Type | Language models |
| Parameters (lead) | 5.2B |
| Variants | 1 |
| Runs with | transformers |
| Based on | Qwen/Qwen3.5-4B-Base |
| Released | 2026-04-20 |
| Popularity | 201 downloads / month |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| AfriqueQwen3.5-4B-ExtendedCM | 5.2B | BF16 | ~11.9 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys afriqueqwen3-5-extendedcm for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (afriqueqwen3-5-extendedcm below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"afriqueqwen3-5-extendedcm","messages":[{"role":"user","content":"Hello"}]}'
Licence
Open weights under cc-by-4.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗