How much memory does Llama 3.2 1B Instruct need at Q4?

The Q4 figure used here is 0.8 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 3.2 1B Instruct at Q4?

GeForce RTX 5050, list price $249.

How fast is Llama 3.2 1B Instruct on the MacBook Pro 14-inch M4 Max 36GB, as a bandwidth estimate?

About 166 tok/s at FP16. That is device bandwidth divided by active weight bytes, not a measured run.

Yes. Llama 3.2 1B Instruct fits on the MacBook Pro 14-inch M4 Max 36GB at FP16, with 22.2 GB of headroom. Usable memory is 25.2 GB.

Can the MacBook Pro 14-inch M4 Max 36GB run Llama 3.2 1B Instruct?

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

Usable memory on this 36 GB unified-memory config is 25.2 GB (70% of the sticker figure). A result under 2 GB of headroom is labeled tight.

Quant ladder

Estimated memory for Llama 3.2 1B Instruct on MacBook Pro 14-inch M4 Max 36GB
Quant	Estimate	Headroom	Est. tok/s	Verdict
Q4	0.8 GB	24.4 GB	508 tok/s	Yes
Q8	1.3 GB	23.9 GB	310 tok/s	Yes
FP16	3.0 GB	22.2 GB	166 tok/s	Yes

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

This machine has one memory pool. Weights are not offloaded to a second bank of system RAM.

Ollama

This command pulls the Q4_K_M file from unsloth/Llama-3.2-1B-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-3.2-1B-Instruct-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 Llama 3.2 1B Instruct · All models for the MacBook Pro 14-inch M4 Max 36GB

Questions

How much memory does Llama 3.2 1B Instruct need at Q4?: The Q4 figure used here is 0.8 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 MacBook Pro 14-inch M4 Max 36GB run Llama 3.2 1B Instruct?: Yes. Llama 3.2 1B Instruct fits on the MacBook Pro 14-inch M4 Max 36GB at FP16, with 22.2 GB of headroom. Usable memory is 25.2 GB.
What is the cheapest catalog device that runs Llama 3.2 1B Instruct at Q4?: GeForce RTX 5050, list price $249.
How fast is Llama 3.2 1B Instruct on the MacBook Pro 14-inch M4 Max 36GB, as a bandwidth estimate?: About 166 tok/s at FP16. That is device bandwidth divided by active weight bytes, not a measured run.