ggml-org
tiny-llamas
- Parameters
- 0B
- Max context length
- 128
- Architecture
- llama
About tiny-llamas
tiny-llamas is a model published in GGUF format. GGUF files are published by ggml-org/tiny-llamas. It has about 24M parameters, the llama architecture, a maximum context length of 128 tokens (values written in the GGUF).
There are 2 quantizations, with file sizes from 0.02 GB (Q4_0) to 0.03 GB (Q8_0) (actual sizes on Hugging Face).
File size and estimated memory per quantization
- Up to 8 GB
- Up to 16 GB
- Up to 24 GB
- Up to 48 GB
- Up to 128 GB
- More
File sizes are the actual values on Hugging Face. Memory is estimated for each context length (KV cache f16). The formula is in How memory is calculated.
All memory figures are Estimated (KV cache f16). It should run on a setup with at least this much VRAM (or Mac unified memory). Click a value to see the devices and models that fit that amount (Find by GPU / Mac).
About the "quality guide" (how far a quantization drifts from the original)
For each quantization type, how far the output drifts from the original model, grouped into six levels from values llama.cpp measured on Llama-3-8B.
The value is mean KLD (the difference between the original and quantized model in next-token probabilities); smaller means closer to the original. Quantizations made with an imatrix (importance data) come out slightly smaller. Levels use the value without an imatrix (or with one, for types that only have that).
These values were not measured on this model. Larger models and MoE models tend to drift less with the same type. Distributor-specific mixed types (such as UD-Q4_K_XL) cannot be matched by type name alone, so they show "-".
| Quantization | Quality guide | KLD (no imatrix) | KLD (imatrix) | Size (Llama-3-8B) |
|---|---|---|---|---|
| Q8_0 | Nearly identical | 0.0014 | - | 7.96 GiB |
| Q6_K | Very small | 0.0055 | - | 6.14 GiB |
| Q5_K_M | Very small | 0.0108 | - | 5.33 GiB |
| Q5_K_S | Small | 0.0166 | - | 5.21 GiB |
| Q5_1 | Small | 0.0180 | - | 5.65 GiB |
| Q5_0 | Small | 0.0222 | - | 5.21 GiB |
| Q4_K_M | Small | 0.0313 | 0.0282 | 4.58 GiB |
| Q4_K_S | Medium | 0.0431 | 0.0320 | 4.37 GiB |
| IQ4_NL | Small | - | 0.0357 | 4.35 GiB |
| IQ4_XS | Small | - | 0.0363 | 4.14 GiB |
| Q4_1 | Medium | 0.0717 | - | 4.78 GiB |
| Q4_0 | Medium | 0.0719 | - | 4.34 GiB |
| Q3_K_L | Medium | 0.0872 | 0.0731 | 4.03 GiB |
| Q3_K_M | Medium | 0.1019 | 0.0844 | 3.74 GiB |
| IQ3_M | Medium | - | 0.1025 | 3.53 GiB |
| IQ3_S | Medium | - | 0.1113 | 3.42 GiB |
| IQ3_XS | Large | - | 0.1387 | 3.28 GiB |
| IQ3_XXS | Large | - | 0.1836 | 3.05 GiB |
| Q3_K_S | Large | 0.2282 | 0.1998 | 3.41 GiB |
| IQ2_M | Large | - | 0.3260 | 2.74 GiB |
| Q2_K | Very large | 0.4451 | 0.3322 | 2.96 GiB |
| Q2_K_S | Very large | - | 0.4034 | 2.96 GiB |
| IQ2_S | Very large | - | 0.4392 | 2.56 GiB |
| IQ2_XS | Very large | - | 0.5463 | 2.43 GiB |
| IQ2_XXS | Very large | - | 0.8120 | 2.24 GiB |
| IQ1_M | Very large | - | 1.3931 | 2.01 GiB |
| IQ1_S | Very large | - | 2.2546 | 1.88 GiB |
Source: llama.cpp (MIT), measured on Llama-3-8B against FP16, Wikitext-2, revision f364eb6f. Original table · Reading and choosing quantizations
Last checked: Oct 30, 2026
- Architecture
- llama
- Supported before llama.cpp b4409
- Parameters
- 0.0B
- Max context length
- 128
| Quantization | File size Measured | Quality guide | 128 max |
|---|---|---|---|
| Q4_0 | 0.02 GB | Medium | 1.09 GB |
| Q8_0 | 0.03 GB | Nearly identical | 1.10 GB |
Ollama ollama run hf.co/ggml-org/tiny-llamas:Q4_0
llama.cpp llama-server -hf ggml-org/tiny-llamas:Q4_0
How to run
Example commands using Q4_0. To use another quantization, replace the name with one from the table above. How to run local LLMs
Ollama
Run it by pointing directly at the GGUF on Hugging Face.
ollama run hf.co/ggml-org/tiny-llamas:Q4_0
llama.cpp
Pass the repository and quantization name to llama-server (or llama-cli) with -hf.
llama-server -hf ggml-org/tiny-llamas:Q4_0
LM Studio
Paste ggml-org/tiny-llamas into the search box, download it, and choose the quantization from the file list.
Other models from ggml-org
-
0B
ggml-org
test-model-router-download
- F16 size
- 0.00 GB
- Memory at 8K
- -
Measured Estimated
-
0.6B
ggml-org
Qwen3-Reranker-0.6B-Q8_0
- Q8_0 size
- 0.64 GB
- Memory at 8K
- 2.43 GB
Measured Estimated VRAM 4 GB+
-
0B
ggml-org
tinygemma3
- Q8_0 size
- 0.05 GB
- Memory at 8K
- 1.20 GB
Measured Estimated VRAM 4 GB+
-
4B
ggml-org
Voxtral-Mini-3B-2507
- Q4_K_M size
- 2.47 GB
- Memory at 8K
- 4.28 GB
Measured Estimated VRAM 4 GB+
-
1.7B
ggml-org
Qwen3-TTS-12Hz-1.7B-Base
- Q4_K_M size
- 1.04 GB
- Memory at 8K
- 3.05 GB
Measured Estimated VRAM 4 GB+
-
ggml-org
stories15M_MOE
- Q8_0 size
- 0.04 GB
- Memory at 8K
- -
Measured Estimated
Models of a similar size (other developers)
-
0B
CompendiumLabs
bge-small-en-v1.5
- Q4_K_M size
- 0.02 GB
- Memory at 8K
- -
Measured Estimated
-
0B
unsloth
bge-small-en-v1.5
- F16 size
- 0.07 GB
- Memory at 8K
- -
Measured Estimated
-
0B
second-state
All-MiniLM-L6-v2-Embedding
- Q4_K_M size
- 0.02 GB
- Memory at 8K
- -
Measured Estimated
-
0B
sentence-transformers
all-MiniLM-L6-v2
- Q4_K_M size
- 0.02 GB
- Memory at 8K
- -
Measured Estimated
-
0B
mixedbread-ai
mxbai-embed-xsmall-v1
- Q8_0 size
- 0.03 GB
- Memory at 8K
- -
Measured Estimated
-
0B
CompendiumLabs
bge-small-zh-v1.5
- Q4_K_M size
- 0.02 GB
- Memory at 8K
- -
Measured Estimated
Frequently asked questions
- How much memory do I need to run tiny-llamas (Q4_0)?
- The file size is 0.02 GB (measured). With a 128-token context, the estimated memory including the KV cache is 1.09 GB. The formula is published at https://localllm.az-arte.com/en/guide/memory-calculation.
- What is the command to run tiny-llamas with Ollama?
- Run "ollama run hf.co/ggml-org/tiny-llamas:Q4_0" to use the GGUF on Hugging Face directly. To use another quantization, replace the name at the end.