LFM2.5 2.6B on M5 Max · 64 GiB

Experiment Unsupported Published

uzu 0.6.17 on M5 Max · 64 GiB, Metal

LFM2.5 2.6B as mirai-l (8-bit), archive 256 input / 128 output: a 256-token prompt and 128 tokens out. Measured 12 Nov 2026, 22:30 UTC by Glenn Sonna, Xybrid.

Doesn’t count in rankings: uzu can't run the frozen prompts: Error: uzu counted 23 input tokens, not the frozen prompt's 26 (measured in qualification).

Experiment id s3-lfm2.5-2.6b-8-bit-uzu-256

Unsupported configuration

uzu can't run the frozen prompts: Error: uzu counted 23 input tokens, not the frozen prompt's 26 (measured in qualification).

Caveats

  • Publisher cards identify the base model but do not always pin the exact export source checkpoint revision.
  • Engines may differ in quantization scheme, effective KV cache precision, kernels, and activations.

Configuration

Device

Device
Apple Mac17,6
Cohort
Apple silicon Macs (desktop)
SoC
Apple M5 Max
CPU
18-core Apple CPU
GPU
Not recorded
NPU
Not recorded
RAM
64.00 GiB
OS
macOS 27.2.0 (26B123)
Kernel
27.2.0
Power
mains
Low power mode
No
Performance mode
Not recorded

Engine

Engine
uzu
Maintainer
Mirai
License
MIT, open source
Version
0.6.17
Commit
Not recorded
Binary SHA-256
7829db228dc9c1a80eb71f2146724ab39c37a2dea37aa760b0cb1558b88e4a7c
Built from
package
Build flags
None
Backend
Metal
Threads
Not recorded
Interface
python-worker
Settings in effect
unsupported=uzu can't run the frozen prompts: Error: uzu counted 23 input tokens, not the frozen prompt's 26 (measured in qualification).

Model and weights

Base model
LFM2.5 2.6B (LFM2.5, 2.6B)
Upstream
LiquidAI/LFM2.5-2.6B@7141b56cd4650af95c7c7b86983443aed050c96a
Weights
trymirai/LFM2.5-2.6B-L@626efec9dff23cd26189db75dd9f90250a00c652
Format
mirai
File 1
README.md · 3,251 bytes · sha256 55c8dc19f11686c7ccfe7b12fb3e41aa0d4c7f0d1740a5be287c650c2e788e69
File 2
config.json · 59,891 bytes · sha256 ae659366b2d7c6c4134c919ed29666dfc0b3c8eadcab00c08e162db276b41671
File 3
model.safetensors · 2.60 GiB · sha256 a963a14d4ea236e2f46e1051c1ad0d97bcbc7f5af9095f63929e824569aa1c1e
File 4
tokenizer.json · 17.1 MiB · sha256 695be7802a0e4b8a81048f0ff5ebb7fc811a0ba5a6be63dbb24deb5a81096f41
Quantization
mirai-l (8-bit)
Weight bits
8
Group size
Not recorded
KV cache
uzu default
Conversion
Published upstream by trymirai
Conversion command
Not recorded

Workload

Workload
Archive 256 input / 128 output
Prompt
256 tokens, from prompts/source.txt
Prompt SHA-256
c10d1b7bef62d95322f8f8d229dc66118d9375107bdc49b06f76287d058b2f6c
Chat template
ea663864491de7ade391839479860ca95541f892f72665c73251fbd4643b1bef
Output
128 tokens, ignoring end of sequence
Context length
4,096
Batch size
1
Sampling
Greedy
Timing
One streamed request per trial
Warmup
2 runs, not counted
Trials planned
6
Cooldown
15 s between trials

Conditions

Ambient
Not recorded
Thermal at start
nominal
Thermal at end
nominal
Thermal gate
macOS thermal state nominal
Throttling detected
Not recorded

Provenance

Measured by
Glenn Sonna, Xybrid
Operator affiliation
Xybrid
Run at
12 Nov 2026, 22:30 UTC
Harness
xybrid-bench 0.4.0 (777cb3d9fecaa7cc1a30694d98492c33dbc6d693)
Methodology
v0.6
Publication
published
Published
16 Nov 2026, 10:23 UTC
Reviewed by
Glenn Sonna

Output check

Result
Not run
Method
Not recorded
Reference
Not recorded
Reference SHA-256
Not recorded
Required passing checks
Not recorded
Detail
Not recorded

Reproduce it

Commands
pnpm bench run --plan plans/s3-lfm2.5-2.6b-8-bit.json

Three palindromic blocks per quantization class and workload; load, two warmups, one trial, unload per turn.

Raw data