Can I run Kolibri-1 on an RX 9060 XT 16GB?
Key facts
No: it needs about 51 GB and this card has 16 GB of graphics memory.
It needs about 50.8 GB at standard quality (estimate). Checked . bartowski Q4_K_M GGUF.
Updated · Kolibri-1 on every card
How much memory it needs
That is about 3.3 times what this card has free.
Get a 1-line alert when a faster quant for Kolibri-1 drops — or when GPUs that run it drop >10%
Get a 1-line alert when a new low-bit GGUF/MLX quant fits 128–256 GB rigs or when multi-GPU & Mac Studio prices drop >10% — weekly, zero spam.
What runs Kolibri-1 instead
The cheapest machine on our list that holds the whole model in its graphics memory:
Mac Studio M4 Max 128GBabout $3,683€3,290
EU shops · Shown to visitors in Europe.US shops · Shown to visitors outside Europe.
We never pass off an estimate as a benchmark. Commissions never change which hardware we recommend. How we calculate
Price details
$3,683€3,290
How we priced this
Not checked against a shop listing (price unverified). Price from 16 Oct 2026.
Used-market euro amount from an earlier check of ours. Used prices cannot be checked on the Apple Store.
Prices excl. shipping unless marked. Euro prices incl. VAT where the seller charges it. Dollar prices are converted from our euro prices without the 21% EU VAT, before US sales tax.
See our picks for Kolibri-1 in Find hardware. Add your budget to see cheaper machines.
For comparison, an RX 9060 XT 16GB costs $522€564, new (cheapest in-stock board on GPU PRIX's German board list). Card details
If you buy through these links we may earn a commission. It doesn't change our ranking. How shop links work
As an Amazon Associate I earn from qualifying purchases.
Als Amazon-Partner verdiene ich an qualifizierten Verkäufen.
Als Amazon-Partner verdien ik aan in aanmerking komende aankopen.
Kolibri-1 on other graphics cards
Runs slowly2
Part of the model spills into normal memory, which is much slower.
Doesn't fit8
Not enough graphics memory: it needs about 50.8 GB.
- RTX 3060 12GBhas 12 GB
- RTX 4060 Ti 16GBhas 16 GB
- RTX 3090has 24 GB
- RTX 4090has 24 GB
- RTX 5080has 16 GB
- RX 9060 XT 16GBhas 16 GB
- RTX 5090has 32 GB
- RX 7900 XTXhas 24 GB
More about the model itself, what it is good at and its licence: Kolibri-1.
The numbers behind this answer
A model comes in several sizes. Q4 is the standard one most people use; the bigger ones answer a little better but need more memory. Each row adds up the model file, the memory a conversation takes, and some working space, and compares the total with what is free on this card.
Swipe the table sideways to see every column.
| Quality | Conversation | Result | Model file | Conversation memory | Working space | Total needed | Free memory |
|---|---|---|---|---|---|---|---|
| Q4 · standard (smallest that keeps quality) | ~12 pages8,192 tokens | Doesn't fit | 49.8 GBmeasured file | 0.2 GB | 0.8 GB | 50.8 GB | 15.4 GB |
| Q5 · a bit sharper, a bit bigger | ~12 pages8,192 tokens | Doesn't fit | 55.5 GB | 0.2 GB | 0.8 GB | 56.5 GB | 15.4 GB |
| Q8 · near full quality, almost twice Q4 | ~12 pages8,192 tokens | Doesn't fit | 83.6 GB | 0.2 GB | 0.8 GB | 84.6 GB | 15.4 GB |
| FP16 · full quality, over three times Q4 | ~12 pages8,192 tokens | Doesn't fit | 156.2 GB | 0.2 GB | 0.8 GB | 157.2 GB | 15.4 GB |
| Q4 · standard, longer conversation | ~49 pages32,768 tokens | Doesn't fit | 49.8 GBmeasured file | 0.7 GB | 0.8 GB | 51.3 GB | 15.4 GB |
speed: not estimated for MoE yet. This model only uses part of itself for each word (a mixture of experts), and our speed estimate does not handle that yet.
Sources and method
Memory and speed on this page are our estimate, not a measured test. Checked . bartowski Q4_K_M GGUF.
Aleph Alpha GmbH's open MoE for German and English, Apache-2.0. The card lists 78,103,074,560 parameters (headline 78B; 78.1B here is that count to one decimal) and 3,457,573,120 active per token (3.46B). Fewer active parameters means less compute per token than a dense model of this total size. That is not a measured tokens-per-second figure: no independent measurement is stored, and speed is not estimated for MoE. 384 experts per layer, 6 active per token, plus a shared expert. llama.cpp b11709 (17 Oct 2026) describes 384 routed experts plus one shared and adds support: https://github.com/ggml-org/llama.cpp/releases/tag/b11709. 50 layers: 40 sliding-window (window 513) and 10 full attention. 48 query heads, 4 KV heads, head dim 128. Config max_position_embeddings is 262,144. The card also validates 1,048,576 tokens and recommends at most 262,144; we use 262,144. The conversation memory in the table is our FP16 estimate on those 10 full layers and the 513-token window. The card evaluates with an FP8 cache for the conversation memory, which our estimate does not use. bartowski GGUF sizes are decimal GB, shards summed, checked 24 Oct 2026 (https://huggingface.co/bartowski/Kolibri-1-GGUF): IQ2_XXS 22.77, Q2_K 29.92, IQ3_XXS 33.65, Q3_K_M 37.62, IQ4_XS 43.63, Q4_K_S 46.40, Q4_K_M 49.76, Q5_K_M 60.30, Q6_K 69.00, Q8_0 83.14, BF16 156.31. The table rounds those files to one decimal. IQ4_XS at 43.63 GB, with the KV and 0.8 GB overhead estimates, fits the 64 GB-class unified-memory machines we score. That fit is our estimate, not a test. Q4_K_M at 49.76 GB does not fit the 64 GB Macs on the same estimate: macOS lets the GPU use about three quarters of 64 GB by default, 48 GB. The 128 GB Macs hold it. The 64 GB Strix Halo row is scored at 48 GB dedicated graphics, enough for IQ4_XS and not for Q4_K_M. The card's own hardware line is about 78 GB of FP8 weights on data-center GPUs; that is a card claim, not a measurement here. The card's release date is 3 Oct 2026. The Hugging Face repo was created 2 Oct 2026. No official Ollama tag, checked 24 Oct 2026.
Questions
- Can I run Kolibri-1 on an RX 9060 XT 16GB?
- No: it needs about 51 GB and this card has 16 GB of graphics memory.
- How much memory does Kolibri-1 need?
- About 50.8 GB at the standard quality (Q4) for a conversation of up to about 12 pages of text (8,192 tokens), by our estimate: 49.8 GB for the model file (measured), 0.2 GB to hold the conversation and 0.8 GB of working space.
- How fast is Kolibri-1 on an RX 9060 XT 16GB?
- We don't give a speed for this model yet. This model only uses part of itself for each word (a mixture of experts), and our speed estimate does not handle that yet.
Speeds and memory are our estimate from the hardware specs, not a measured test. Prices are dated and may change. How we calculate