How much memory does DeepSeek R1 Distill Llama 8B need at Q4?

The Q4 figure used here is 6.0 GB. GGUF file size plus an FP16 KV-cache estimate at 8,192 tokens. The cache counts only the layers and heads named in the method on the About page.

What is the cheapest catalog device that runs DeepSeek R1 Distill Llama 8B at Q4?

GeForce RTX 5050, list price $249.

How fast is DeepSeek R1 Distill Llama 8B on the GeForce RTX 4090, as a bandwidth estimate?

About 62.8 tok/s at FP16. That is device bandwidth divided by active weight bytes, not a measured run.

Yes. DeepSeek R1 Distill Llama 8B fits on the GeForce RTX 4090 at FP16, with 3.5 GB of headroom. Usable memory is 22.8 GB.

Can the GeForce RTX 4090 run DeepSeek R1 Distill Llama 8B?

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

Usable memory on this 24 GB VRAM config is 22.8 GB (95% of the sticker figure). A result under 2 GB of headroom is labeled tight.

Quant ladder

Estimated memory for DeepSeek R1 Distill Llama 8B on GeForce RTX 4090
Quant	Estimate	Headroom	Est. tok/s	Verdict
Q4	6.0 GB	16.8 GB	205 tok/s	Yes
Q8	9.6 GB	13.2 GB	118 tok/s	Yes
FP16	19.3 GB	3.5 GB	62.8 tok/s	Yes

GGUF file size plus an FP16 KV-cache estimate at 8,192 tokens. The cache counts only the layers and heads named in the method on the About page.
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

FP16 KV-cache estimate: 1.1 GB at 8,192 tokens and 4.3 GB at 32,768 tokens. GQA counts two tensors (K and V) for the stored KV heads and head dimension.

Offload

The Q4 weight estimate fits in usable VRAM, so this page does not assume a system-RAM offload.

Ollama

This command pulls the Q4_K_M file from unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF, the Hub repo whose file size is used above. It is not an official Ollama library tag.

ollama run hf.co/unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF:Q4_K_M

Other picks

Cheapest catalog device at Q4: GeForce RTX 5050
Closest catalog model that still fits at Q4: Qwen3.6 35B-A3B.

All hardware for DeepSeek R1 Distill Llama 8B · All models for the GeForce RTX 4090

Questions

How much memory does DeepSeek R1 Distill Llama 8B need at Q4?: The Q4 figure used here is 6.0 GB. GGUF file size plus an FP16 KV-cache estimate at 8,192 tokens. The cache counts only the layers and heads named in the method on the About page.
Can the GeForce RTX 4090 run DeepSeek R1 Distill Llama 8B?: Yes. DeepSeek R1 Distill Llama 8B fits on the GeForce RTX 4090 at FP16, with 3.5 GB of headroom. Usable memory is 22.8 GB.
What is the cheapest catalog device that runs DeepSeek R1 Distill Llama 8B at Q4?: GeForce RTX 5050, list price $249.
How fast is DeepSeek R1 Distill Llama 8B on the GeForce RTX 4090, as a bandwidth estimate?: About 62.8 tok/s at FP16. That is device bandwidth divided by active weight bytes, not a measured run.