Mixtral 8x7B Instruct v0.1 vs Mixtral 8x7B v0.1
Side-by-side comparison of VRAM requirements, quantization, context length, and hardware compatibility.
Specifications
| Mixtral 8x7B Instruct v0.1 | Mixtral 8x7B v0.1 | |
|---|---|---|
| Parameters | 46.7B | 46.7B |
| Context | 33K | 33K |
| Architecture | MixtralForCausalLM | MixtralForCausalLM |
| License | Apache 2.0 | Apache 2.0 |
| Downloads | 874.9K | 76.9K |
| Released | — | — |
VRAM by Quantization: Mixtral 8x7B Instruct v0.1 vs Mixtral 8x7B v0.1
| Quantization | Bits | Mixtral 8x7B Instruct v0.1 VRAM | Mixtral 8x7B v0.1 VRAM |
|---|---|---|---|
| Q2_K | 3.40 | 20.4 GB | 20.4 GB |
| Q3_K_M | 3.90 | 23.3 GB | 23.3 GB |
| Q3_K_S | 3.50 | 21 GB | 21 GB |
| Q4_0 | 4.00 | 23.9 GB | 23.9 GB |
| Q4_K_M | 4.80 | 28.6 GB | 28.6 GB |
| Q5_K_M | 5.70 | 33.8 GB | 33.8 GB |
| Q6_K | 6.60 | 39.1 GB | 39.1 GB |
| Q8_0 | 8.00 | 47.3 GB | 47.3 GB |
Verdict
Mixtral 8x7B Instruct v0.1 is the more widely downloaded of the two.
Frequently Asked Questions
- Which needs less VRAM, Mixtral 8x7B Instruct v0.1 or Mixtral 8x7B v0.1?
At Q4_K_M, Mixtral 8x7B Instruct v0.1 needs 28.6 GB and Mixtral 8x7B v0.1 needs 28.6 GB, so Mixtral 8x7B Instruct v0.1 is the lighter option to run locally.
- Which has a longer context window, Mixtral 8x7B Instruct v0.1 or Mixtral 8x7B v0.1?
Mixtral 8x7B Instruct v0.1 supports 32,768 tokens and Mixtral 8x7B v0.1 supports 32,768 tokens.
- What is the difference between Mixtral 8x7B Instruct v0.1 and Mixtral 8x7B v0.1?
Mixtral 8x7B Instruct v0.1 is a 46.7B model from Mistral AI (Mixtral family), while Mixtral 8x7B v0.1 is a 46.7B model from Mistral AI (Mixtral family). Compare their VRAM requirements above to see which fits your GPU or Mac.