trlm 135m needs about 0.8 GB of memory at Q4_K_M (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 19 quants, from 0.1 GB (Q2_K) to 0.5 GB (F32).
Tiny reasoning model with 135M parameters
The trlm-135m model is a 135M parameter research prototype built on a Llama‑based backbone. It is fine‑tuned for step‑by‑step reasoning through a three‑stage pipeline. The model is available in multiple GGUF quantizations.
Good at
- Step‑by‑step reasoning
- Instruction following
- Low‑parameter inference
Limits
- Not production‑ready; hallucinations common
- English‑only
- Limited general knowledge
Best for
- Research on small reasoning models
- Educational demos
- Low‑resource inference
Who it’s for. Researchers and developers interested in exploring how small models can learn reasoning. It is suitable for experimentation and educational purposes rather than production use.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.1 GB | 0.8 GB | Fits | Get file → | |
| Q3_K_S | 0.1 GB | 0.8 GB | Fits | Get file → | |
| Q4_0 | 0.1 GB | 0.8 GB | Fits | Get file → | |
| Q3_K_M | 0.1 GB | 0.8 GB | Fits | Get file → | |
| Q3_K_L | 0.1 GB | 0.8 GB | Fits | Get file → | |
| Q4_1 | 0.1 GB | 0.8 GB | Fits | Get file → | |
| Q4_K_S | 0.1 GB | 0.8 GB | Fits | Get file → | |
| Q5_0 | 0.1 GB | 0.8 GB | Fits | Get file → | |
| Q4_K | 0.1 GB | 0.8 GB | Fits | Get file → | |
| Q4_K_M | 0.1 GB | 0.8 GB | Fits | Get file → | |
| Q5_K_S | 0.1 GB | 0.8 GB | Fits | Get file → | |
| Q5_1 | 0.1 GB | 0.8 GB | Fits | Get file → | |
| Q5_K | 0.1 GB | 0.8 GB | Fits | Get file → | |
| Q5_K_M | 0.1 GB | 0.8 GB | Fits | Get file → | |
| Q6_K | 0.1 GB | 0.8 GB | Fits | Get file → | |
| Q8_0 | 0.1 GB | 0.8 GB | Fits | Get file → | |
| BF16 | 0.3 GB | 1.0 GB | Fits | Get file → | |
| F16 | 0.3 GB | 1.0 GB | Fits | Get file → | |
| F32 | 0.5 GB | 1.2 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M or Q5_K_M (file size 0.11 GB, estimated memory 0.8 GB). For 16 GB VRAM, Q8_0 or F16 (file size 0.14 GB or 0.27 GB, estimated memory 0.8 GB or 1 GB). Higher precision quants like F32 require 1.2 GB memory and 0.54 GB file size.
What GPU do you need for trlm 135m?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is F32 (0.5 GB file, about 1.2 GB in use).
Which trlm 135m quant should you choose?
Q4_K_M is the usual starting point for trlm 135m: it balances file size and quality well. Here it is a 0.1 GB file.
The Q8_0 file is 0.1 GB, about 1.4 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 0.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about trlm 135m
How much VRAM does trlm 135m need?
About 0.8 GB at Q4_K_M with an 8K context window. That is the 0.1 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run trlm 135m on an 8 GB GPU?
Yes, with F32: the 0.5 GB file needs about 1.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of trlm 135m GGUF?
It depends on the quant: Q2_K is 0.1 GB, Q3_K_S is 0.1 GB, Q4_0 is 0.1 GB, Q3_K_M is 0.1 GB, Q3_K_L is 0.1 GB, Q4_1 is 0.1 GB and 13 more.
What context length does trlm 135m support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.2 GB at 8K.
Where can I download trlm 135m GGUF?
The files are on Hugging Face in the prithivMLmods/trlm-135m-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does trlm 135m use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run trlm-135m on 8 GB VRAM?
Yes, use Q4_K_M or Q5_K_M quants; they require about 0.8 GB memory at 8k context.
Does the model support vision tasks?
No, the model is a text‑only Llama‑based model.
What license applies to this model?
The model is released under the apache-2.0 license.