Bielik 11B v3.1 Instruct — VRAM, speed & local setup
Written by Jakub Rusinowski · Last updated
The newest Bielik: 11B, pre-trained on 56 languages with the emphasis on Polish and European languages, then tuned with supervised fine-tuning and reinforcement learning. It adds reasoning (reasoning_effort from none to max) and native tool calling; both need SpeakLeash's bielik-tools parsers on vLLM 0.24 or newer. The chat template prepends a built-in system prompt of about 1,000 tokens, which can be turned off. The repository is gated: accept the conditions on Hugging Face first.
Bielik 11B v3.1 Instruct needs about 8 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.
VRAM and speed by quantization
Quoted against NVIDIA RTX 4090 (24 GB). Includes the KV cache at 8K context, so it reads higher than the headline figure.
| Quant | Memory | VRAM | Speed (est.) | Fit |
|---|---|---|---|---|
| Q2_K 2.63 bpw | 6.1 GB | ~122 tok/s | Fits | |
| Q3_K_M 3.41 bpw | 7.2 GB | ~104 tok/s | Fits | |
| Q4_K_M 4.83 bpw | 9.2 GB | ~81 tok/s | Fits | |
| Q5_K_M 5.67 bpw | 10.4 GB | ~72 tok/s | Fits | |
| Q6_K 6.56 bpw | 11.6 GB | ~65 tok/s | Fits | |
| Q8_0 8.50 bpw | 14.3 GB | ~52 tok/s | Fits | |
| F16 16.00 bpw | 24.8 GB | ~5 tok/s | Offload |
Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. Bielik 11B v3.1 Instruct VRAM calculator →
Get Bielik 11B v3.1 Instruct running
The cheapest catalogued GPU that runs Bielik 11B v3.1 Instruct is the Intel Arc B570 (10 GB).
or compare on Vast.ai from $0.35/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
How to run Bielik 11B v3.1 Instruct
No Ollama tag. SpeakLeash publishes an official GGUF (Q4_K_M 6.7 GB) for llama.cpp, plus MLX, FP8, NVFP4 and AWQ builds.
Specifications
Verified — Checked against the primary source — the model card or the vendor spec page — and corroborated by a second independent source.
- Parameters
- 11 Billion
- Context window
- 32,768
- Architecture
- Dense transformer (50 layers, GQA)
- Provider
- SpeakLeash / ACK Cyfronet AGH
- Licence
- Apache-2.0
- Availability
- Weights downloadable
- Access
- Gated: request access on Hugging Face and accept the licence first
- Practical deployment
- Laptop
- Specified at
- Q4_K_M
- System RAM
- 16 GB
- Record updated
- 2026-11-11
- Runs with
- vLLM: supported source llama.cpp: supported source
Commercial use permitted. No usage restrictions beyond attribution.
Limits and caveats
- Reasoning and tool calling need the speakleash/bielik-tools vLLM parsers (vLLM 0.24 or newer); plain llama.cpp chat works without them.
- The built-in system prompt takes about 1,000 tokens of the context unless you disable it.
- SpeakLeash publishes DFlash speculative-decoding drafters for this model.
See also Bielik PL 11B v3.0 Instruct
Quality and use cases
Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.
Other Bielik sizes
Bielik 11B v3.1 Instruct — frequently asked questions
How much VRAM does Bielik 11B v3.1 Instruct need?
About 8 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does Bielik 11B v3.1 Instruct run on an RTX 4090 (24 GB)?
Yes. Bielik 11B v3.1 Instruct needs about 8 GB at Q4_K_M, inside a 24 GB card, at an estimated 81 tokens/sec.
How do I run Bielik 11B v3.1 Instruct locally?
No Ollama tag. SpeakLeash publishes an official GGUF (Q4_K_M 6.7 GB) for llama.cpp, plus MLX, FP8, NVFP4 and AWQ builds. Running the published tag would send your prompts to a hosted GPU rather than your own machine.
What other sizes does Bielik come in?
Bielik PL 11B v3.0 Instruct (7 GB), Bielik 11B v3.1 Instruct (8 GB), Bielik 11B v3.0 (multilingual) (8 GB), Bielik Minitron 7B v3.0 Instruct (5 GB), Bielik PL Minitron 7B v3.0 Instruct (5 GB), Bielik 4.5B v3.0 Instruct (4 GB), Bielik 1.5B v3.0 Instruct (2 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.