Leaderboard / SpeakLeash (Bielik)
Bielik 11B v3 Instruct
SpeakLeash (Bielik) · Bielik · released 2025-11-07 · data checked 2026-11-01 Needs verification
Bielik 11B v3 Instruct is a 11.2B-parameter dense model from SpeakLeash (Bielik) (Europe), released 2025-11-07 under the Apache-2.0 license. It doesn't have enough reported benchmarks for an index score yet. It needs about 8.8 GB of memory at 4-bit with an 8K-token context.
Polish-first model from the SpeakLeash community and ACK Cyfronet AGH.
Benchmarks
Each bar shows this model's score. The tick marks the best small model on that benchmark.
No benchmark results for this release yet. Know of one? Send it.
Specifications
- Lab
- SpeakLeash (Bielik) (PL · Europe)
- Architecture
- Dense transformer
- Total parameters
- 11.2B
- Active parameters
- All (dense)
- Size class
- Small
- Context window
- 32K tokens
- Input modalities
- text
- Reasoning
- Instruct (no thinking)
- License
- Apache-2.0
- Openness
- Open weights
- Memory to run
- ~8.8 GB at 4-bit, 8K context (more sizes)
- Hugging Face
- 2.8K downloads (30 days) · 156 likes
Compare with
- Bielik 11B v3 Instruct vs Gemma 4 12B (11.9B, index 56.9)
- Bielik 11B v3 Instruct vs Gemma 3 12B (12.2B, index 28.4)
- Bielik 11B v3 Instruct vs MiniCPM-SALA (9.5B, index 52.6)
Sources
Something wrong here? Report it.
Run it locally
Uses speakleash/Bielik-11B-v3.0-Instruct-GGUF (Q4_K_M). Swap the tag for another size: BF16, F16, Q4_K_M, Q5_K_M, Q6_K, Q8_0.
ollama run hf.co/speakleash/Bielik-11B-v3.0-Instruct-GGUF:Q4_K_Mllama-server -hf speakleash/Bielik-11B-v3.0-Instruct-GGUF:Q4_K_Mpip install -U mlx-lm
mlx_lm.chat --model speakleash/Bielik-11B-v3.0-Instruct-MLX-4bitvllm serve speakleash/Bielik-11B-v3.0-InstructMemory needed: weights, context cache and runtime buffers (context cache estimated: attention layout not published).
| Quantization | 4K context | 32K context |
|---|---|---|
| 16-bit F16 | 24 GB | 28 GB |
| 8-bit Q8_0 | 13 GB | 18 GB |
| 4-bit Q4_K_M | 8.1 GB | 12 GB |