LocalFit
Submit a benchmark

Olmo-Hybrid-7B Base

allenai/Olmo-Hybrid-7B

Released2026-03-05Size7.4B tensors · denseRoleBaseLicenseapache-2.0Context64K config max

Where it runs 8K context · ≥ 5 t/s floor

SetupBest planMemoryGenerate
8 GB GPU + 32 GB RAMnative BF16vLLMGPU streams weights from RAM · 9 GiB in RAMFits*≤ 3.3 t/s Ceiling
12 GB GPU + 32 GB RAMnative BF16vLLMGPU streams weights from RAM · 5 GiB in RAMFits*≤ 5.7 t/s Ceiling
16 GB GPU + 64 GB RAMnative BF16vLLMGPU streams weights from RAM · 1 GiB in RAMFits*≤ 38 t/s Ceiling
24 GB GPU + 64 GB RAMnative BF16vLLMFull GPUFits*≤ 66 t/s Ceiling
32 GB GPU + 128 GB RAMnative BF16vLLMFull GPUFits*≤ 117 t/s Ceiling
2× 24 GB GPUs + 128 GB RAMnative BF16vLLMFull GPUFits*≤ 61 t/s Ceiling
96 GB workstation GPU + 256 GB RAMnative BF16vLLMFull GPUFits*≤ 117 t/s Ceiling
Mac, 24 GBDoes not fit
Mac, 48 GBDoes not fit
Mac, 128 GBDoes not fit
Mac, 512 GBDoes not fit
DGX Spark 128 GBnative BF16vLLMUnified memoryFits*≤ 18 t/s Ceiling
Ryzen AI Max+ 395, 128 GBnative BF16vLLMUnified memoryFits*≤ 17 t/s Ceiling
CPU only, 64 GB DDR5-5600 dual channelDoes not fit

Same plan engine as the planner, with its default reserves and RAM. How plans are chosen.

Files exact Hugging Face bytes

ArtifactSizeFilesRevisionSource
Native safetensors BF16
allenai/Olmo-Hybrid-7B
13.84 GiB14f1cc566f9HF files

Not found in the representative quant search (not proven unavailable): GGUF FP16, GGUF Q8_0, GGUF Q5_K_M, GGUF Q4_K_M, MLX 8-bit, MLX 4-bit, EXL3, AWQ, GPTQ. Complete selected file sets; projectors, MTP/draft and lookup files are listed separately and budgeted only by plans that use them. File bytes are not allocated memory.

Quality

No Artificial Analysis evaluation mapped to this checkpoint.

Arena text rating

Unknown

Publisher-reported benchmarks

None extracted from the model card.

AA and Arena describe the hosted model in the stated mode, not each quantized file; scores are never inherited by base, pruned, abliterated or quantized variants and never averaged together.

How to run it

Transformers · unknown

publisher-documented, not executed source

pip install "transformers>=5.3.0"
from transformers import AutoModelForCausalLM, AutoTokenizer
olmo = AutoModelForCausalLM.from_pretrained("allenai/Olmo-Hybrid-7B")
tokenizer = AutoTokenizer.from_pretrained("allenai/Olmo-Hybrid-7B")
message = ["Language modeling is "]
inputs = tokenizer(message, return_tensors='pt', return_token_type_ids=False)
# optional verifying cuda
# inputs = {k: v.to('cuda') for k,v in inputs.items()}
# olmo = olmo.to('cuda')
response = olmo.generate(**inputs, max_new_tokens=100, do_sample=True, top_k=0, temperature=1.0, top_p=0.7)
print(tokenizer.batch_decode(response, skip_special_tokens=True)[0])
>> 'Language modeling is a fundamental task in natural language processing (NLP) that involves predicting the next word in a sequence given   
  the previous words. It has been widely used in various NLP applications such as machine translation, speech recognition, and text         
  generation...'

Prerequisites: transformers>=5.3.0; quote version constraint in shell toavoidredirection.

  • Base completion model; no final hybrid chat/RL checkpoint is listed.
  • 24 DeltaNet layers need recurrent state; 8 full attention layers grow with context.

Recipes are source examples (settings are the publisher’s or author’s, not measured optima) and were not executed by LocalFit. A downloadable file does not prove your backend build supports the architecture.

Reported speeds 0

No reported measurement yet. Submit one.