M1 8GB

APPLE · 8GB unified memory · 2 reports

On the M1 8GB, LFM2.5 2.6B at 4-bit, the model most run on it, generates a median of 22.0 tokens per second from one plain run (community reports, as of 29 Oct 2026).

As of 29 Oct 2026, the models most run on the M1 8GB, with generation and prompt-processing medians from plain runs (one device, one request, no speculative decoding):

LFM2.5 2.6B
22.0gen t/s at 4-bit · one run
PP 200.0 t/s · 1 run

Engines people use on it: llama.cpp 1 (reports)

See reported performance Estimate what fits

How to compare these reports →Filter reports by setup →All M1 Macs compared →

Run models on your M1 8GB? Add your numbers.

Your coding agent can run a speed test on your machine and send it here with a free account. Or paste a result you've already posted.

Benchmark with your agent Paste a result

Reported performance on the M1 8GB

These reports mix GPU counts and memory setups, so a model listed here may have needed extra cards or CPU offloading. The calculator estimates which models fit in 8 GB of unified memory.

This page is thin (2 of 3 reports needed for indexing). Help fill it in.

Date ↓Date ↑Token speed ↓Token speed ↑Prefill ↓Prefill ↑Context ↓Context ↑Ranked

LFM2.5 2.6B

M1 8GB · llama.cpp · 32,000 ctx

generation:: 22.0 tokens/s
prompt processing (prefill):: 200.0 tokens/s
quant:: QAD-Q4_0 (GGUF)

Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is input throughput, not time to first token. Check the full setup before comparing.

agentictool-use

User compares LFM2.5 2.6B and MiniCPM5 2B on small agentic tool-use tasks on an M1 Air. LFM2.5 2.6B runs at 200 t/s prompt and 22 t/s generation with llama.cpp, QAD-Q4_0 GGUF, 32k context, using about 2.5 GB of RAM. MiniCPM5 2B runs at 162 t/s prompt and 16 t/s generation with a DSpark draft model, Q8_0 GGUF, 32k context, q5_1 KV cache, using about 3.8 GB of RAM. User calls LFM2.5 the clear winner: faster, less RAM despite more parameters, and better aligned for English conversation. MiniCPM5 is noted as often responding in Chinese and hallucinating less, but LFM2.5 tends to hallucinate as conversations get longer.

Gemma 4 5.1B E2B

M1 8GB · Ollama

generation:: 15-20 tokens/s
quant:: Q4 (GGUF)

Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is shown only when the source reports it; generation speed cannot tell us time to first token. Check the full setup before comparing.

text-generation

User reports Gemma 4 at 15-20 t/s, a range the user calls usable for simple tasks.

Get a weekly email of new M1 8GB reports and newly released models that fit it.

Email me new reports

Reported configurations

Individual observations from this page, not expected speeds or a ranking. Select a model to open its report, with the source and offloading conditions. Reported context may be a limit rather than actual input length.

Model / hardware	Quant / engine	Reported context	Generation
LFM2.5 2.6B M1 8GB	QAD-Q4_0 llama.cpp	32,000	22.0 tokens/s

Frequently asked

How fast is the M1 8GB for local LLMs?

On the M1 8GB, LFM2.5 2.6B at 4-bit, the model most run on it, generates a median of 22.0 tokens per second from one plain run (community reports, as of 29 Oct 2026).