Kolibri 1 — Hardware Requirements & GPU Compatibility
ChatReasoningFunctions
Kolibri 1 is a 78.1B-parameter open language model from Aleph-Alpha. It supports a context window of up to 262,144 tokens. At Q4_K_M it needs about 47.25 GB of VRAM — see which GPUs and Macs can run it below.
8.5K downloads
845 likesSpecifications
- Publisher
- Aleph-Alpha
- Parameters
- 78.1B
- Architecture
- Kolibri1ForCausalLM
- Context Length
- 262,144 tokens
- Vocabulary Size
- 128,000
- Release Date
- 2026-10-02
- License
- Apache 2.0
Get Started
HuggingFace
Run in cloud
Fits on A100 80GB (32 GB headroom) · Q4_K_M
- Generation speed
- ~231 tok/s
- generation speed
- Cost per 1M output tokens
- $1.30
- per 1M output tokens
How Much VRAM Does Kolibri 1 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 33.6 GB | 44.7 GB | 33.19 GB | 2-bit quantization with K-quant improvements |
| Q3_K_M | 3.90 | 38.5 GB | 49.6 GB | 38.08 GB | 3-bit medium quantization |
| Q4_K_M | 4.80 | 47.3 GB | 58.4 GB | 46.86 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 56.0 GB | 67.1 GB | 55.65 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 64.8 GB | 75.9 GB | 64.44 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 78.5 GB | 89.6 GB | 78.10 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 156.6 GB | 167.7 GB | 156.21 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run Kolibri 1?
Q4_K_M · 47.3 GBKolibri 1 (Q4_K_M) requires 47.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 62+ GB is recommended. Using the full 262K context window can add up to 11.1 GB, bringing total usage to 58.4 GB. No consumer GPU has enough memory.
Which Devices Can Run Kolibri 1?
Q4_K_M · 47.3 GB23 devices with unified memory can run Kolibri 1, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Studio M4 Max (64 GB).
Runs great
— Plenty of headroom
Where to Download Kolibri 1
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Frequently Asked Questions
- How much VRAM does Kolibri 1 need?
Kolibri 1 requires 47.3 GB of VRAM at Q4_K_M, or 156.6 GB at BF16. Full 262K context adds up to 11.1 GB (58.4 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 78.1B × 4.8 bits ÷ 8 = 46.9 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 11.5 GB (at full 262K context)
VRAM usage by quantization
Q4_K_M47.3 GBQ4_K_M + full context58.4 GB- Can NVIDIA GeForce RTX 5090 run Kolibri 1?
No — Kolibri 1 requires at least 33.6 GB at Q2_K, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- What's the best quantization for Kolibri 1?
For Kolibri 1, Q4_K_M (47.3 GB) offers the best balance of quality and VRAM usage. Q5_K_M (56.0 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 33.6 GB.
VRAM requirement by quantization
Q2_K33.6 GBQ4_K_M ★47.3 GBQ5_K_M56.0 GBQ6_K64.8 GBQ8_078.5 GBBF16156.6 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Kolibri 1 on a Mac?
Yes, but only at lower quantizations. The smallest Mac that can run Kolibri 1 is Mac Mini M4 Pro (48 GB) at Q2_K; 13 of the 39 Macs we list can run it at some quantization. For Q4_K_M (47.3 GB) you need a Mac with more unified memory.
- Can I run Kolibri 1 locally?
Yes — Kolibri 1 can run locally on consumer hardware. At Q4_K_M quantization it needs 47.3 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Kolibri 1?
At Q4_K_M, Kolibri 1 can reach ~96 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = 1000 ÷ (active GB ÷ (bandwidth GB/s × efficiency) × 1000 + layers × routing ms)
Mixture-of-Experts: only the active experts are read per token, plus a fixed per-layer routing cost.
Example: NVIDIA B200 → 2.1 GB active ÷ (8000 × 0.65) = 0.40 ms, plus 50 layers × 0.055 ms = 2.75 ms, so 1000 ÷ 3.15 ms = ~317 tok/s
Estimated speed at Q4_K_M (47.3 GB)
~317 tok/s~317 tok/s~294 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Kolibri 1?
At Q4_K_M, the download is about 46.86 GB. The full-precision BF16 version is 156.21 GB. The smallest option (Q2_K) is 33.19 GB.
- Which GPUs can run Kolibri 1?
No single consumer GPU has enough VRAM to run Kolibri 1 at Q4_K_M (47.3 GB). Multi-GPU or professional hardware is required.
- Which devices can run Kolibri 1?
23 devices with unified memory can run Kolibri 1 at Q4_K_M (47.3 GB), including ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.