How much memory does Llama 4 Scout need at Q4?

The Q4 figure used here is 65.4 GB. GGUF file size from the linked Hub repo. KV cache was not added, because this model's attention shape is not in the catalog.

What is the cheapest catalog device that runs Llama 4 Scout at Q4?

Framework Desktop 128GB, list price $3,449.

How fast is Llama 4 Scout on the GeForce RTX 5090, as a bandwidth estimate?

About 175 tok/s at Q4. That is device bandwidth divided by active weight bytes, not a measured run.

No. Llama 4 Scout does not fit on the GeForce RTX 5090 at Q4. The estimate is 65.4 GB and usable memory is 30.4 GB.

Can the GeForce RTX 5090 run Llama 4 Scout?

Data updated 16 October 2026. Last reviewed the same day, when this catalog snapshot was written.

Usable memory on this 32 GB VRAM config is 30.4 GB (95% of the sticker figure). A result under 2 GB of headroom is labeled tight.

Quant ladder

Estimated memory for Llama 4 Scout on GeForce RTX 5090
Quant	Estimate	Headroom	Est. tok/s	Verdict
Q4	65.4 GB	-35.0 GB	175 tok/s	No
Q8	115 GB	-84.1 GB	100.0 tok/s	No
FP16	261 GB	-230.3 GB	52.7 tok/s	No

GGUF file size from the linked Hub repo. KV cache was not added, because this model's attention shape is not in the catalog.
Formula estimate: parameter count × bytes per weight × 1.20. No GGUF file size is stored for this quant.
Tokens/sec is a bandwidth roofline: GB/s divided by active weight GB. It is not a measured generation speed.

KV cache at 8K and 32K

No KV-cache estimate. The public config for this model was gated, missing, or not a GQA or MLA shape this catalog knows how to read.

Offload

About 35.0 GB of the Q4 weights sit outside usable VRAM. A partial offload would need at least that much free system RAM. This catalog does not record system RAM, so offload is not counted as a fit.

Ollama

This command pulls the Q4_K_M file from unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF, the Hub repo whose file size is used above. It is not an official Ollama library tag.

ollama run hf.co/unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF:Q4_K_M

What fits instead

Cheapest catalog device at Q4: Framework Desktop 128GB
Closest catalog model that still fits at Q4: Mixtral 8x7B.

All hardware for Llama 4 Scout · All models for the GeForce RTX 5090

Questions

How much memory does Llama 4 Scout need at Q4?: The Q4 figure used here is 65.4 GB. GGUF file size from the linked Hub repo. KV cache was not added, because this model's attention shape is not in the catalog.
Can the GeForce RTX 5090 run Llama 4 Scout?: No. Llama 4 Scout does not fit on the GeForce RTX 5090 at Q4. The estimate is 65.4 GB and usable memory is 30.4 GB.
What is the cheapest catalog device that runs Llama 4 Scout at Q4?: Framework Desktop 128GB, list price $3,449.
How fast is Llama 4 Scout on the GeForce RTX 5090, as a bandwidth estimate?: About 175 tok/s at Q4. That is device bandwidth divided by active weight bytes, not a measured run.